@article{bb219200,
        AUTHOR = "Liao, H.S. and Chen, L. and Song, Y. and Ming, H.",
        TITLE = "Visualization-Based Active Learning for Video Annotation",
        JOURNAL = MultMed,
        VOLUME = "18",
        YEAR = "2016",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "2196-2205",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214206"}

@article{bb219201,
        AUTHOR = "Chou, C.L. and Chen, H.T. and Lee, S.Y.",
        TITLE = "Multimodal Video-to-Near-Scene Annotation",
        JOURNAL = MultMed,
        VOLUME = "19",
        YEAR = "2017",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "354-366",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214207"}

@article{bb219202,
        AUTHOR = "Wang, H. and Wu, X.X. and Jia, Y.D.",
        TITLE = "Heterogeneous domain adaptation method for video annotation",
        JOURNAL = IET-CV,
        VOLUME = "11",
        YEAR = "2017",
        NUMBER = "2",
        MONTH = "March",
        PAGES = "181-187",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214208"}

@article{bb219203,
        AUTHOR = "Li, W. and Guo, D. and Fang, X.Z.",
        TITLE = "Multimodal architecture for video captioning with memory networks and
an attention mechanism",
        JOURNAL = PRL,
        VOLUME = "105",
        YEAR = "2018",
        PAGES = "23-29",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214209"}

@article{bb219204,
        AUTHOR = "Protasov, S. and Khan, A.M. and Sozykin, K. and Ahmad, M.",
        TITLE = "Using deep features for video scene detection and annotation",
        JOURNAL = SIViP,
        VOLUME = "12",
        YEAR = "2018",
        NUMBER = "5",
        MONTH = "July",
        PAGES = "991-999",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214210"}

@article{bb219205,
        AUTHOR = "Shetty, R. and Tavakoli, H.R. and Laaksonen, J.",
        TITLE = "Image and Video Captioning with Augmented Neural Architectures",
        JOURNAL = MultMedMag,
        VOLUME = "25",
        YEAR = "2018",
        NUMBER = "2",
        MONTH = "April",
        PAGES = "34-46",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214211"}

@article{bb219206,
        AUTHOR = "Yang, Y. and Zhou, J. and Ai, J. and Bin, Y. and Hanjalic, A. and Shen, H.T. and Ji, Y.",
        TITLE = "Video Captioning by Adversarial LSTM",
        JOURNAL = IP,
        VOLUME = "27",
        YEAR = "2018",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "5600-5611",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214212"}

@article{bb219207,
        AUTHOR = "Gao, L.L. and Li, X.P. and Song, J.K. and Shen, H.T.",
        TITLE = "Hierarchical LSTMs with Adaptive Attention for Visual Captioning",
        JOURNAL = PAMI,
        VOLUME = "42",
        YEAR = "2020",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "1112-1131",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214213"}

@article{bb219208,
        AUTHOR = "Zhang, X.X. and Zhu, Z.F. and Zhao, Y. and Chang, D.X.",
        TITLE = "Learning a General Assignment Model for Video Analytics",
        JOURNAL = CirSysVideo,
        VOLUME = "28",
        YEAR = "2018",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "3066-3076",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214214"}

@article{bb219209,
        AUTHOR = "Daskalakis, E. and Tzelepi, M. and Tefas, A.",
        TITLE = "Learning deep spatiotemporal features for video captioning",
        JOURNAL = PRL,
        VOLUME = "116",
        YEAR = "2018",
        PAGES = "143-149",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214215"}

@article{bb219210,
        AUTHOR = "Xu, N. and Liu, A. and Wong, Y. and Zhang, Y. and Nie, W. and Su, Y. and Kankanhalli, M.",
        TITLE = "Dual-Stream Recurrent Neural Network for Video Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "29",
        YEAR = "2019",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "2482-2493",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214216"}

@article{bb219211,
        AUTHOR = "Ren, J.H. and Zhang, W.S.",
        TITLE = "CLOSE: Coupled content-semantic embedding",
        JOURNAL = SIViP,
        VOLUME = "13",
        YEAR = "2019",
        NUMBER = "6",
        MONTH = "September",
        PAGES = "1087-1095",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214217"}

@article{bb219212,
        AUTHOR = "Lee, J. and Kim, J.",
        TITLE = "Exploring the effects of non-local blocks on video captioning networks",
        JOURNAL = IJCVR,
        VOLUME = "9",
        YEAR = "2019",
        NUMBER = "5",
        PAGES = "502-514",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214218"}

@inproceedings{bb219213,
        AUTHOR = "Mun, J. and Yang, L.J. and Ren, Z. and Xu, N. and Han, B.H.",
        TITLE = "Streamlined Dense Video Captioning",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6581-6590",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214219"}

@article{bb219214,
        AUTHOR = "Wang, H.Y. and Gao, C.Y. and Han, Y.H.",
        TITLE = "Sequence in sequence for video captioning",
        JOURNAL = PRL,
        VOLUME = "130",
        YEAR = "2020",
        PAGES = "327-334",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214220"}

@article{bb219215,
        AUTHOR = "Harwath, D. and Recasens, A. and Suris, D. and Chuang, G. and Torralba, A.B. and Glass, J.",
        TITLE = "Jointly Discovering Visual Objects and Spoken Words from Raw Sensory
Input",
        JOURNAL = IJCV,
        VOLUME = "128",
        YEAR = "2020",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "620-641",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214221"}

@inproceedings{bb219216,
        AUTHOR = "Glass, J. and Torralba, A.B. and Chuang, G. and Suris, D. and Recasens, A. and Harwath, D.",
        TITLE = "Jointly Discovering Visual Objects and Spoken Words from Raw Sensory
Input",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "VI: 659-677",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214221"}

@article{bb219217,
        AUTHOR = "Wei, R. and Mi, L. and Hu, Y.S. and Chen, Z.Z.",
        TITLE = "Exploiting the local temporal information for video captioning",
        JOURNAL = JVCIR,
        VOLUME = "67",
        YEAR = "2020",
        PAGES = "102751",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214222"}

@article{bb219218,
        AUTHOR = "Zhang, J.C. and Peng, Y.X.",
        TITLE = "Video Captioning With Object-Aware Spatio-Temporal Correlation and
Aggregation",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        PAGES = "6209-6222",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214223"}

@inproceedings{bb219219,
        AUTHOR = "Zhang, J.C. and Peng, Y.X.",
        TITLE = "Object-Aware Aggregation With Bidirectional Temporal Graph for Video
Captioning",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "8319-8328",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214224"}

@article{bb219220,
        AUTHOR = "Xiao, H.H. and Shi, J.L.",
        TITLE = "Video captioning with text-based dynamic attention and step-by-step
learning",
        JOURNAL = PRL,
        VOLUME = "133",
        YEAR = "2020",
        PAGES = "305-312",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214225"}

@article{bb219221,
        AUTHOR = "Ning, K. and Cai, M. and Xie, D. and Wu, F.",
        TITLE = "An Attentive Sequence to Sequence Translator for Localizing Video
Clips by Natural Language",
        JOURNAL = MultMed,
        VOLUME = "22",
        YEAR = "2020",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "2434-2443",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214226"}

@article{bb219222,
        AUTHOR = "Wu, A. and Han, Y. and Yang, Y. and Hu, Q. and Wu, F.",
        TITLE = "Convolutional Reconstruction-to-Sequence for Video Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "30",
        YEAR = "2020",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "4299-4308",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214227"}

@article{bb219223,
        AUTHOR = "Tu, Y.B. and Zhou, C. and Guo, J.J. and Gao, S.X. and Yu, Z.T.",
        TITLE = "Enhancing the alignment between target words and corresponding frames
for video captioning",
        JOURNAL = PR,
        VOLUME = "111",
        YEAR = "2021",
        PAGES = "107702",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214228"}

@article{bb219224,
        AUTHOR = "Boran, E. and Erdem, A. and Ikizler Cinbis, N. and Erdem, E. and Madhyastha, P. and Specia, L.",
        TITLE = "Leveraging auxiliary image descriptions for dense video captioning",
        JOURNAL = PRL,
        VOLUME = "146",
        YEAR = "2021",
        PAGES = "70-76",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214229"}

@article{bb219225,
        AUTHOR = "Wang, T. and Zheng, H. and Yu, M.J. and Tian, Q. and Hu, H.F.",
        TITLE = "Event-Centric Hierarchical Representation for Dense Video Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "31",
        YEAR = "2021",
        NUMBER = "5",
        PAGES = "1890-1900",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214230"}

@article{bb219226,
        AUTHOR = "Xu, W. and Yu, J. and Miao, Z.J. and Wan, L. and Tian, Y. and Ji, Q.",
        TITLE = "Deep Reinforcement Polishing Network for Video Captioning",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "1772-1784",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214231"}

@article{bb219227,
        AUTHOR = "Zhang, Z.W. and Xu, D. and Ouyang, W.L. and Zhou, L.P.",
        TITLE = "Dense Video Captioning Using Graph-Based Sentence Summarization",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "1799-1810",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214232"}

@article{bb219228,
        AUTHOR = "Liu, S. and Ren, Z. and Yuan, J.S.",
        TITLE = "SibNet: Sibling Convolutional Encoder for Video Captioning",
        JOURNAL = PAMI,
        VOLUME = "43",
        YEAR = "2021",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "3259-3272",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214233"}

@article{bb219229,
        AUTHOR = "Yan, Y.C. and Zhuang, N. and Ni, B.B. and Zhang, J. and Xu, M.H. and Zhang, Q. and Zhang, Z. and Cheng, S. and Tian, Q. and Xu, Y. and Yang, X.K. and Zhang, W.J.",
        TITLE = "Fine-Grained Video Captioning via Graph-based Multi-Granularity
Interaction Learning",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "666-683",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214234"}

@article{bb219230,
        AUTHOR = "Deng, J. and Li, L. and Zhang, B. and Wang, S.H. and Zha, Z.J. and Huang, Q.M.",
        TITLE = "Syntax-Guided Hierarchical Attention Network for Video Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "32",
        YEAR = "2022",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "880-892",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214235"}

@article{bb219231,
        AUTHOR = "Hua, X. and Wang, X.Q. and Rui, T. and Shao, F. and Wang, D.",
        TITLE = "Adversarial Reinforcement Learning With Object-Scene Relational Graph
for Video Captioning",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "2004-2016",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214236"}

@article{bb219232,
        AUTHOR = "Wang, L.X. and Li, H.L. and Qiu, H.Q. and Wu, Q.B. and Meng, F.M. and Ngan, K.N.",
        TITLE = "POS-Trends Dynamic-Aware Model for Video Caption",
        JOURNAL = CirSysVideo,
        VOLUME = "32",
        YEAR = "2022",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "4751-4764",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214237"}

@article{bb219233,
        AUTHOR = "Xue, P. and Zhou, B.",
        TITLE = "Exploring the Spatio-Temporal Aware Graph for video captioning",
        JOURNAL = IET-CV,
        VOLUME = "16",
        YEAR = "2022",
        NUMBER = "5",
        PAGES = "456-467",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214238"}

@article{bb219234,
        AUTHOR = "Niu, T.Z. and Dong, S.S. and Chen, Z.D. and Luo, X. and Huang, Z. and Guo, S. and Xu, X.S.",
        TITLE = "A multi-layer memory sharing network for video captioning",
        JOURNAL = PR,
        VOLUME = "136",
        YEAR = "2023",
        PAGES = "109202",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214239"}

@article{bb219235,
        AUTHOR = "Tu, Y. and Zhou, C. and Guo, J.J. and Li, H.F. and Gao, S.X. and Yu, Z.T.",
        TITLE = "Relation-aware attention for video captioning via graph learning",
        JOURNAL = PR,
        VOLUME = "136",
        YEAR = "2023",
        PAGES = "109204",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214240"}

@inproceedings{bb219236,
        AUTHOR = "Shao, H.L. and Fang, Z.Y. and Yang, Y.Z.",
        TITLE = "CAVAN: Commonsense Knowledge Anchored Video Captioning",
        BOOKTITLE = "ICPR22",
        YEAR = "2022",
        PAGES = "4095-4102",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214241"}

@inproceedings{bb219237,
        AUTHOR = "Guo, Z.X. and Wang, T.J.J. and Laaksonen, J.",
        TITLE = "Post-Attention Modulator for Dense Video Captioning",
        BOOKTITLE = "ICPR22",
        YEAR = "2022",
        PAGES = "1536-1542",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214242"}

@inproceedings{bb219238,
        AUTHOR = "Yamazaki, K. and Truong, S. and Vo, K. and Kidd, M. and Rainwater, C. and Luu, K. and Le, N.",
        TITLE = "VLCAP: Vision-Language with Contrastive Learning for Coherent Video
Paragraph Captioning",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "3656-3661",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214243"}

@inproceedings{bb219239,
        AUTHOR = "Lebron, L. and Graham, Y. and O'Connor, N.E. and McGuinness, K.",
        TITLE = "Evaluation of Automatically Generated Video Captions Using Vision and
Language Models",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "2416-2420",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214244"}

@inproceedings{bb219240,
        AUTHOR = "Chatzikonstantinou, C. and Valasidis, G.G. and Stavridis, K. and Malogiannis, G. and Axenopoulos, A. and Daras, P.",
        TITLE = "UCF-CAP, Video Captioning in the Wild",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "1386-1390",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214245"}

@inproceedings{bb219241,
        AUTHOR = "Zhang, Q. and Song, Y.Q. and Jin, Q.",
        TITLE = "Unifying Event Detection and Captioning as Sequence Generation via
Pre-training",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXVI:363-379",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214246"}

@inproceedings{bb219242,
        AUTHOR = "Bi, T.Y. and Jarnikov, D. and Lukkien, J.",
        TITLE = "Shot-Based Hybrid Fusion for Movie Genre Classification",
        BOOKTITLE = CIAP22,
        YEAR = "2022",
        PAGES = "I:257-269",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214247"}

@inproceedings{bb219243,
        AUTHOR = "Fish, E. and Weinbren, J. and Gilbert, A.",
        TITLE = "Rethinking Genre Classification With Fine Grained Semantic Clustering",
        BOOKTITLE = ICIP21,
        YEAR = "2021",
        PAGES = "1274-1278",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214248"}

@inproceedings{bb219244,
        AUTHOR = "Zhu, M.J.",
        TITLE = "Video Captioning in Compressed Video",
        BOOKTITLE = ICIVC21,
        YEAR = "2021",
        PAGES = "336-341",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214249"}

@inproceedings{bb219245,
        AUTHOR = "Lin, X.D. and Bertasius, G. and Wang, J. and Chang, S.F. and Parikh, D. and Torresani, L.",
        TITLE = "VX2TEXT: End-to-End Learning of Video-Based Text Generation From
Multimodal Inputs",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "7001-7011",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214250"}

@inproceedings{bb219246,
        AUTHOR = "Liao, Y.H. and Kar, A. and Fidler, S.",
        TITLE = "Towards Good Practices for Efficiently Annotating Large-Scale Image
Classification Datasets",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "4348-4357",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214251"}

@inproceedings{bb219247,
        AUTHOR = "Song, Y.Q. and Chen, S.Z. and Jin, Q.",
        TITLE = "Towards Diverse Paragraph Captioning for Untrimmed Videos",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "11240-11249",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214252"}

@inproceedings{bb219248,
        AUTHOR = "Chen, S. and Jiang, Y.G.",
        TITLE = "Towards Bridging Event Captioner and Sentence Localizer for Weakly
Supervised Dense Event Captioning",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "8421-8431",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214253"}

@inproceedings{bb219249,
        AUTHOR = "Deng, C.R. and Chen, S.Z. and Chen, D. and He, Y. and Wu, Q.",
        TITLE = "Sketch, Ground, and Refine: Top-Down Dense Video Captioning",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "234-243",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214254"}

@inproceedings{bb219250,
        AUTHOR = "Zhang, Z. and Qi, Z.A. and Yuan, C.F. and Shan, Y. and Li, B. and Deng, Y. and Hu, W.M.",
        TITLE = "Open-book Video Captioning with Retrieve-Copy-Generate Network",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "9832-9841",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214255"}

@inproceedings{bb219251,
        AUTHOR = "Perez Martin, J. and Bustos, B. and Perez, J.",
        TITLE = "Improving Video Captioning with Temporal Composition of a
Visual-Syntactic Embedding*",
        BOOKTITLE = WACV21,
        YEAR = "2021",
        PAGES = "3038-3048",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214256"}

@inproceedings{bb219252,
        AUTHOR = "Muller Budack, E. and Springstein, M. and Hakimov, S. and Mrutzek, K. and Ewerth, R.",
        TITLE = "Ontology-driven Event Type Classification in Images",
        BOOKTITLE = WACV21,
        YEAR = "2021",
        PAGES = "2927-2937",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214257"}

@inproceedings{bb219253,
        AUTHOR = "Hosseinzadeh, M. and Wang, Y.",
        TITLE = "Video Captioning of Future Frames",
        BOOKTITLE = WACV21,
        YEAR = "2021",
        PAGES = "979-988",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214258"}

@inproceedings{bb219254,
        AUTHOR = "Knights, J. and Harwood, B. and Ward, D. and Vanderkop, A. and Mackenzie Ross, O. and Moghadam, P.",
        TITLE = "Temporally Coherent Embeddings for Self-Supervised Video
Representation Learning",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "8914-8921",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214259"}

@inproceedings{bb219255,
        AUTHOR = "Rimle, P. and Dogan Schonberger, P. and Gross, M.",
        TITLE = "Enriching Video Captions With Contextual Text",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "5474-5481",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214260"}

@inproceedings{bb219256,
        AUTHOR = "Bi, T.Y. and Jarnikov, D. and Lukkien, J.",
        TITLE = "Video Representation Fusion Network For Multi-Label Movie Genre
Classification",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "9386-9391",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214261"}

@inproceedings{bb219257,
        AUTHOR = "Poorgholi, S. and Kayhan, O.S. and van Gemert, J.C.",
        TITLE = "t-eva: Time-efficient t-sne Video Annotation",
        BOOKTITLE = HCAU20,
        YEAR = "2020",
        PAGES = "153-169",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214262"}

@inproceedings{bb219258,
        AUTHOR = "Ai, J.B. and Yang, Y. and Xu, X. and Zhou, J. and Shen, H.T.",
        TITLE = "CC-LSTM: Cross and Conditional Long-short Time Memory for Video
Captioning",
        BOOKTITLE = MMDLCA20,
        YEAR = "2020",
        PAGES = "353-365",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214263"}

@inproceedings{bb219259,
        AUTHOR = "Zheng, Q. and Wang, C. and Tao, D.",
        TITLE = "Syntax-Aware Action Targeting for Video Captioning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "13093-13102",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214264"}

@inproceedings{bb219260,
        AUTHOR = "Zhang, Z. and Shi, Y. and Yuan, C. and Li, B. and Wang, P. and Hu, W. and Zha, Z.",
        TITLE = "Object Relational Graph With Teacher-Recommended Learning for Video
Captioning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "13275-13285",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214265"}

@inproceedings{bb219261,
        AUTHOR = "lashin, V. and Rahtu, E.",
        TITLE = "Multi-modal Dense Video Captioning",
        BOOKTITLE = MULWS20,
        YEAR = "2020",
        PAGES = "4117-4126",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214266"}

@inproceedings{bb219262,
        AUTHOR = "Pan, B. and Cai, H. and Huang, D. and Lee, K. and Gaidon, A. and Adeli, E. and Niebles, J.C.",
        TITLE = "Spatio-Temporal Graph for Video Captioning With Knowledge
Distillation",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10867-10876",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214267"}

@inproceedings{bb219263,
        AUTHOR = "Liu, J.Z. and Chen, W. and Cheng, Y. and Gan, Z. and Yu, L.C. and Yang, Y.M. and Liu, J.J.",
        TITLE = "Violin: A Large-Scale Dataset for Video-and-Language Inference",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10897-10907",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214268"}

@inproceedings{bb219264,
        AUTHOR = "da Silva, J.L. and Tabata, A.N. and Broto, L.C. and Cocron, M.P. and Zimmer, A. and Brandmeier, T.",
        TITLE = "Open Source Multipurpose Multimedia Annotation Tool",
        BOOKTITLE = ICIAR20,
        YEAR = "2020",
        PAGES = "I:356-367",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214269"}

@inproceedings{bb219265,
        AUTHOR = "Cherian, A. and Wang, J. and Hori, C. and Marks, T.K.",
        TITLE = "Spatio-Temporal Ranked-Attention Networks for Video Captioning",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "1606-1615",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214270"}

@inproceedings{bb219266,
        AUTHOR = "Hemalatha, M. and Sekhar, C.C.",
        TITLE = "Domain-Specific Semantics Guided Approach to Video Captioning",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "1576-1585",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214271"}

@inproceedings{bb219267,
        AUTHOR = "Wang, B. and Ma, L. and Zhang, W. and Jiang, W. and Wang, J. and Liu, W.",
        TITLE = "Controllable Video Captioning With POS Sequence Guidance Based on
Gated Fusion Network",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "2641-2650",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214272"}

@inproceedings{bb219268,
        AUTHOR = "Hou, J. and Wu, X. and Zhao, W. and Luo, J. and Jia, Y.",
        TITLE = "Joint Syntax Representation Learning and Visual Cue Translation for
Video Captioning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "8917-8926",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214273"}

@inproceedings{bb219269,
        AUTHOR = "Pei, W.J. and Zhang, J.Y. and Wang, X.R. and Ke, L. and Shen, X.Y. and Tai, Y.W.",
        TITLE = "Memory-Attended Recurrent Network for Video Captioning",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "8339-8348",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214274"}

@inproceedings{bb219270,
        AUTHOR = "Aafaq, N. and Akhtar, N. and Liu, W. and Gilani, S.Z. and Mian, A.",
        TITLE = "Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual
Encoding for Video Captioning",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "12479-12488",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214275"}

@inproceedings{bb219271,
        AUTHOR = "Fuhl, W. and Castner, N. and Zhuang, L. and Holzer, M. and Rosenstiel, W. and Kasneci, E.",
        TITLE = "MAM: Transfer Learning for Fully Automatic Video Annotation and
Specialized Detector Creation",
        BOOKTITLE = Egocentric18,
        YEAR = "2018",
        PAGES = "V:375-388",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214276"}

@inproceedings{bb219272,
        AUTHOR = "Sun, X.Y. and Chen, P.H. and Chen, L.W. and Li, C.H. and Li, T.H. and Tan, M.K. and Gan, C.",
        TITLE = "Masked Motion Encoding for Self-Supervised Video Representation
Learning",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "2235-2245",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214277"}

@inproceedings{bb219273,
        AUTHOR = "Huang, D. and Wu, W.H. and Hu, W.W. and Liu, X. and He, D.L. and Wu, Z.H. and Wu, X.M. and Tan, M.K. and Ding, E.",
        TITLE = "ASCNet: Self-Supervised Video Representation Learning with
Appearance-Speed Consistency",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "8076-8085",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214278"}

@inproceedings{bb219274,
        AUTHOR = "Gan, C. and Gong, B.Q. and Liu, K. and Su, H. and Guibas, L.J.",
        TITLE = "Geometry Guided Convolutional Neural Networks for Self-Supervised
Video Representation Learning",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "5589-5597",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214279"}

@inproceedings{bb219275,
        AUTHOR = "Liu, D. and Zhou, Y. and Sun, X. and Zha, Z. and Zeng, W.",
        TITLE = "Adaptive Pooling in Multi-instance Learning for Web Video Annotation",
        BOOKTITLE = WSM17,
        YEAR = "2017",
        PAGES = "318-327",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214280"}

@inproceedings{bb219276,
        AUTHOR = "Marwah, T. and Mittal, G. and Balasubramanian, V.N.",
        TITLE = "Attentive Semantic Video Generation Using Captions",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1435-1443",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214281"}

@inproceedings{bb219277,
        AUTHOR = "Krishna, R. and Hata, K. and Ren, F. and Fei Fei, L. and Niebles, J.C.",
        TITLE = "Dense-Captioning Events in Videos",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "706-715",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214282"}

@inproceedings{bb219278,
        AUTHOR = "Kalboussi, R. and Abdellaoui, M. and Douik, A.",
        TITLE = "Video Saliency Detection Based on Boolean Map Theory",
        BOOKTITLE = CIAP17,
        YEAR = "2017",
        PAGES = "I:119-128",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214283"}

@inproceedings{bb219279,
        AUTHOR = "Pobar, M. and Ivasic Kos, M.",
        TITLE = "Multi-label Poster Classification into Genres Using Different Problem
Transformation Methods",
        BOOKTITLE = CAIP17,
        YEAR = "2017",
        PAGES = "II: 367-378",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214284"}

@inproceedings{bb219280,
        AUTHOR = "Sageder, G. and Zaharieva, M. and Breiteneder, C.",
        TITLE = "Group Feature Selection for Audio-Based Video Genre Classification",
        BOOKTITLE = MMMod16,
        YEAR = "2016",
        PAGES = "I: 29-41",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214285"}

@inproceedings{bb219281,
        AUTHOR = "Mori, M. and Kimiyama, H. and Ogawara, M.",
        TITLE = "Search-Based Content Analysis System on Online Collaborative Platform
for Film Production",
        BOOKTITLE = ICPR14,
        YEAR = "2014",
        PAGES = "1091-1096",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214286"}

@inproceedings{bb219282,
        AUTHOR = "Jang, W.D. and Lee, C. and Sim, J.Y. and Kim, C.S.",
        TITLE = "Automatic Video Genre Classification Using Multiple SVM Votes",
        BOOKTITLE = ICPR14,
        YEAR = "2014",
        PAGES = "2655-2660",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214287"}

@inproceedings{bb219283,
        AUTHOR = "Almeida, J. and Guimaraes Pedronette, D.C. and Penatti, O.A.B.",
        TITLE = "Unsupervised Manifold Learning for Video Genre Retrieval",
        BOOKTITLE = CIARP14,
        YEAR = "2014",
        PAGES = "604-612",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214288"}

@inproceedings{bb219284,
        AUTHOR = "Ding, X.M. and Li, B. and Hu, W.M. and Xiong, W.H. and Wang, Z.C.",
        TITLE = "Context-aware horror video scene recognition via cost-sensitive sparse
coding",
        BOOKTITLE = ICPR12,
        YEAR = "2012",
        PAGES = "1904-1907",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214289"}

@inproceedings{bb219285,
        AUTHOR = "Ionescu, B. and Vertan, C. and Lambert, P. and Benoit, A.",
        TITLE = "A color-action perceptual approach to the classification of animated
movies",
        BOOKTITLE = ICMR11,
        YEAR = "2011",
        PAGES = "10",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214290"}

@inproceedings{bb219286,
        AUTHOR = "Strat, S.T. and Benoit, A. and Bredin, H. and Quenot, G. and Lambert, P.",
        TITLE = "Hierarchical Late Fusion for Concept Detection in Videos",
        BOOKTITLE = Concept12,
        YEAR = "2012",
        PAGES = "III: 335-344",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214291"}

@inproceedings{bb219287,
        AUTHOR = "Nagaraja, N.S. and Ochs, P. and Liu, K. and Brox, T.",
        TITLE = "Hierarchy of Localized Random Forests for Video Annotation",
        BOOKTITLE = DAGM12,
        YEAR = "2012",
        PAGES = "21-30",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214292"}

@inproceedings{bb219288,
        AUTHOR = "Tsapanos, N. and Nikolaidis, N. and Pitas, I.",
        TITLE = "Towards automated post-production and semantic annotation of films",
        BOOKTITLE = ICIIP11,
        YEAR = "2011",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214293"}

@inproceedings{bb219289,
        AUTHOR = "Li, B. and Hu, W.M. and Xiong, W.H. and Wu, O. and Li, W.",
        TITLE = "Horror Image Recognition Based on Emotional Attention",
        BOOKTITLE = ACCV10,
        YEAR = "2010",
        PAGES = "II: 594-605",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214294"}

@inproceedings{bb219290,
        AUTHOR = "Wang, J.C. and Li, B. and Hu, W.M. and Wu, O.",
        TITLE = "Horror movie scene recognition based on emotional perception",
        BOOKTITLE = ICIP10,
        YEAR = "2010",
        PAGES = "1489-1492",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214295"}

@inproceedings{bb219291,
        AUTHOR = "Chen, J.F. and Lu, H. and Wei, R.Z. and Jin, C. and Xue, X.Y.",
        TITLE = "An effective method for video genre classification",
        BOOKTITLE = CIVR10,
        YEAR = "2010",
        PAGES = "97-104",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214296"}

@inproceedings{bb219292,
        AUTHOR = "Kowdle, A. and Chang, K.W. and Chen, T.H.",
        TITLE = "Video categorization using object of interest detection",
        BOOKTITLE = ICIP10,
        YEAR = "2010",
        PAGES = "4569-4572",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214297"}

@inproceedings{bb219293,
        AUTHOR = "Petersohn, C.",
        TITLE = "Temporal video structuring for preservation and annotation of video
content",
        BOOKTITLE = ICIP09,
        YEAR = "2009",
        PAGES = "93-96",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214298"}

@inproceedings{bb219294,
        AUTHOR = "Wang, F.S. and Lu, W. and Liu, J.G. and Shah, M. and Xu, D.",
        TITLE = "Automatic video annotation with adaptive number of key words",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214299"}

@inproceedings{bb219295,
        AUTHOR = "Kutics, A. and Nakagawa, A. and Shindoh, K.",
        TITLE = "Use of Adaptive Still Image Descriptors for Annotation of Video Frames",
        BOOKTITLE = ICIAR07,
        YEAR = "2007",
        PAGES = "686-697",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214300"}

@inproceedings{bb219296,
        AUTHOR = "Wang, F.S. and Xu, D. and Lu, W. and Xu, H.L.",
        TITLE = "Automatic Annotation and Retrieval for Videos",
        BOOKTITLE = PSIVT06,
        YEAR = "2006",
        PAGES = "1030-1040",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214301"}

@inproceedings{bb219297,
        AUTHOR = "Rosten, E. and Reitmayr, G. and Drummond, T.W.",
        TITLE = "Real-Time Video Annotations for Augmented Reality",
        BOOKTITLE = ISVC05,
        YEAR = "2005",
        PAGES = "294-302",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214302"}

@inproceedings{bb219298,
        AUTHOR = "Caspi, Y. and Bargeron, D.",
        TITLE = "Sharing video annotations",
        BOOKTITLE = ICIP04,
        YEAR = "2004",
        PAGES = "IV: 2227-2230",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214303"}

@inproceedings{bb219299,
        AUTHOR = "Wang, M. and Zhou, X.D. and Chua, T.S.",
        TITLE = "Automatic image annotation via local multi-label classification",
        BOOKTITLE = CIVR08,
        YEAR = "2008",
        PAGES = "17-26",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT214304"}

Last update:Mar 25, 2024 at 16:07:51