@inproceedings{bb239700,
AUTHOR = "Bhattacharjee, S.S. and Campbell, D. and Shome, R.",
TITLE = "Believing is Seeing: Unobserved Object Detection using Generative
Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19366-19377",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234617"}
@inproceedings{bb239701,
AUTHOR = "Zhou, E. and Su, Q. and Chi, C. and Zhang, Z.Z. and Wang, Z.Y. and Huang, T.J. and Sheng, L. and Wang, H.",
TITLE = "Code-as-Monitor: Constraint-aware Visual Programming for Reactive and
Proactive Robotic Failure Detection",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "6919-6929",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234618"}
@inproceedings{bb239702,
AUTHOR = "Zhou, W.J. and Tao, M. and Zhao, C.Y. and Guo, H.Y. and Dong, H.H. and Tang, M. and Wang, J.Q.",
TITLE = "PhysVLM: Enabling Visual Language Models to Understand Robotic
Physical Reachability",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "6940-6949",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234619"}
@inproceedings{bb239703,
AUTHOR = "Song, C.H. and Blukis, V. and Tremblay, J. and Tyree, S. and Su, Y. and Birchfield, S.",
TITLE = "RoboSpatial: Teaching Spatial Understanding to 2D and 3D
Vision-Language Models for Robotics",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "15768-15780",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234620"}
@inproceedings{bb239704,
AUTHOR = "Lozano, A. and Sun, M.W. and Burgess, J. and Chen, L. and Nirschl, J.J. and Gu, J. and Lopez, I. and Aklilu, J. and Rau, A. and Katzer, A.W. and Zhang, Y.H. and Chiu, C. and Wang, X.H. and Song, A.S. and Tibshirani, R. and Yeung Levy, S.",
TITLE = "BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and
Vision-Language Models Derived from Scientific Literature",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19724-19735",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234621"}
@inproceedings{bb239705,
AUTHOR = "Xiao, R. and Kim, S. and Georgescu, M.I. and Akata, Z. and Alaniz, S.",
TITLE = "FLAIR: VLM with Fine-grained Language-informed Image Representations",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24884-24894",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234622"}
@inproceedings{bb239706,
AUTHOR = "Zhang, J.M. and Ye, J. and Ma, X. and Li, Y. and Yang, Y.F. and Chen, Y.H. and Sang, J. and Yeung, D.Y.",
TITLE = "Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on
Vision-language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19900-19909",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234623"}
@inproceedings{bb239707,
AUTHOR = "Wang, X. and Chen, K. and Zhang, J.M. and Chen, J.J. and Ma, X.",
TITLE = "TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in
Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19910-19920",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234624"}
@inproceedings{bb239708,
AUTHOR = "Vasu, P.K.A. and Faghri, F. and Li, C.L. and Koc, C. and True, N. and Antony, A. and Santhanam, G. and Gabriel, J. and Grasch, P. and Tuzel, O. and Pouransari, H.",
TITLE = "FastVLM: Efficient Vision Encoding for Vision Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19769-19780",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234625"}
@inproceedings{bb239709,
AUTHOR = "Chen, Q.Z. and Wang, C. and Wang, D. and Zhang, T. and Li, W. and He, X.F.",
TITLE = "Lifelong Knowledge Editing for Vision Language Models with Low-Rank
Mixture-of-Experts",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "9455-9466",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234626"}
@inproceedings{bb239710,
AUTHOR = "Chen, T.Y. and Fu, X.C. and Gao, Y. and Qian, H.D. and Wei, Y. and Yan, K. and Zhou, H.Y. and Li, J.X.",
TITLE = "Galaxy Walker: Geometry-aware VLMs For Galaxy-scale Understanding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4112-4121",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234627"}
@inproceedings{bb239711,
AUTHOR = "Liu, Z.J. and Zhu, L. and Shi, B. and Zhang, Z.Y. and Lou, Y.M. and Yang, S. and Xi, H.C. and Cao, S.Y. and Gu, Y.X. and Li, D.C. and Li, X. and Tang, H.T. and Fang, Y.H. and Chen, Y. and Hsieh, C.Y. and Huang, D.A. and Cheng, A.C. and Hu, J.Y. and Liu, S. and Krishna, R. and Molchanov, P. and Kautz, J. and Yin, H.X. and Han, S. and Lu, Y.",
TITLE = "NVILA: Efficient Frontier Visual Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4122-4134",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234628"}
@inproceedings{bb239712,
AUTHOR = "Poppi, T. and Kasarla, T. and Mettes, P. and Baraldi, L. and Cucchiara, R.",
TITLE = "Hyperbolic Safety-Aware Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4222-4232",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234629"}
@inproceedings{bb239713,
AUTHOR = "Zhang, H.Y. and Guo, Y.Y. and Kankanhalli, M.",
TITLE = "Joint Vision-Language Social Bias Removal for CLIP",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4246-4255",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234630"}
@inproceedings{bb239714,
AUTHOR = "Zhang, Y. and Deng, Y.X. and Guo, M.H. and Hu, S.M.",
TITLE = "Adaptive Parameter Selection for Tuning Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4280-4290",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234631"}
@inproceedings{bb239715,
AUTHOR = "Deng, A. and Cao, T. and Chen, Z. and Hooi, B.",
TITLE = "Words or Vision: Do Vision-Language Models Have Blind Faith in Text?",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3867-3876",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234632"}
@inproceedings{bb239716,
AUTHOR = "Huang, R. and Ding, X.P. and Wang, C.W. and Han, J.H. and Liu, Y.L. and Zhao, H.S. and Xu, H. and Hou, L. and Zhang, W. and Liang, X.D.",
TITLE = "HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large
Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29814-29824",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234633"}
@inproceedings{bb239717,
AUTHOR = "Wang, S. and Zhang, Y.J. and Zhu, Y. and Li, J.N. and Wang, Z.Z. and Liu, Y.W. and Ji, X.Y.",
TITLE = "Towards Understanding How Knowledge Evolves in Large Vision-Language
Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29858-29868",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234634"}
@inproceedings{bb239718,
AUTHOR = "Deitke, M. and Clark, C. and Lee, S.H. and Tripathi, R. and Yang, Y. and Park, J.S. and Salehi, M. and Muennighoff, N. and Lo, K. and Soldaini, L. and Lu, J. and Anderson, T. and Bransom, E. and Ehsani, K. and Ngo, H. and Chen, Y. and Patel, A. and Yatskar, M. and Callison Burch, C. and Head, A. and Hendrix, R. and Bastani, F. and VanderBilt, E. and Lambert, N. and Chou, Y. and Chheda, A. and Sparks, J. and Skjonsberg, S. and Schmitz, M. and Sarnat, A. and Bischoff, B. and Walsh, P. and Newell, C. and Wolters, P. and Gupta, T. and Zeng, K.H. and Borchardt, J. and Groeneveld, D. and Nam, C. and Lebrecht, S. and Wittlif, C. and Schoenick, C. and Michel, O. and Krishna, R. and Weihs, L. and Smith, N.A. and Hajishirzi, H. and Girshick, R. and Farhadi, A. and Kembhavi, A.",
TITLE = "Molmo and PixMo: Open Weights and Open Data for State-of-the-Art
Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "91-104",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234635"}
@inproceedings{bb239719,
AUTHOR = "Zhao, W. and Han, Y.Z. and Tang, J.S. and Li, Z. and Song, Y.B. and Wang, K. and Wang, Z.Y. and You, Y.",
TITLE = "A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for
Accelerating Large VLMs",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19814-19824",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234636"}
@inproceedings{bb239720,
AUTHOR = "Lee, B.K. and Hachiuma, R. and Wang, Y.C.A.F. and Ro, Y.M. and Wu, Y.H.",
TITLE = "VLsI: Verbalized Layers-to-Interactions from Large to Small Vision
Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29545-29557",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234637"}
@inproceedings{bb239721,
AUTHOR = "Sun, J.C. and Sharma, R. and Lokhande, V.S. and Chen, C.Y.",
TITLE = "Cross-Modal Feature Alignment and MMD Improve Robustness of Prompt
Tuning",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4714-4724",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234638"}
@inproceedings{bb239722,
AUTHOR = "Safaei, B. and Patel, V.M.",
TITLE = "Active Learning for Vision-Language Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4902-4912",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234639"}
@inproceedings{bb239723,
AUTHOR = "Wang, Y.C. and Zhang, Z.K. and Wang, J. and Fan, D. and Xu, Z.L. and Liu, L. and Hao, X. and Bhat, V. and Li, X.Y.",
TITLE = "GEXIA: Granularity Expansion and Iterative Approximation for Scalable
Multi-Grained Video-Language Learning",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4725-4735",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234640"}
@inproceedings{bb239724,
AUTHOR = "Colman, R. and Vu, M. and Bhattarai, M. and Ma, M. and Viswanathan, H. and O'Malley, D. and Santos, J.E.",
TITLE = "PatchFinder: Leveraging Visual Language Models for Accurate
Information Retrieval Using Model Uncertainty",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "9146-9155",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234641"}
@inproceedings{bb239725,
AUTHOR = "Jawade, B. and Soares, J.V.B. and Thadani, K. and Mohan, D.D. and Eshratifar, A.E. and Culpepper, B. and de Juan, P. and Setlur, S. and Govindaraju, V.",
TITLE = "SCOT: Self-Supervised Contrastive Pretraining for Zero-Shot
Compositional Retrieval",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5509-5519",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234642"}
@inproceedings{bb239726,
AUTHOR = "Talemi, N.A. and Kashiani, H. and Afghah, F.",
TITLE = "Style-Pro: Style-Guided Prompt Learning for Generalizable
Vision-Language Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6207-6216",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234643"}
@inproceedings{bb239727,
AUTHOR = "Chang, H.S. and Wang, C.Y. and Wang, R.R. and Chou, G. and Liao, H.Y.M.",
TITLE = "Generalist YOLO: Towards Real-Time End-to-End Multi-Task Visual
Language Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6217-6227",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234644"}
@inproceedings{bb239728,
AUTHOR = "Westfechtel, T. and Zhang, D. and Harada, T.",
TITLE = "Combining Inherent Knowledge of Vision-Language Models with
Unsupervised Domain Adaptation Through Strong-Weak Guidance",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6528-6537",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234645"}
@inproceedings{bb239729,
AUTHOR = "Chen, H.N. and Ni, Y. and Huang, W.J. and Liu, Y. and Jeong, S. and Wen, F. and Bastian, N.D. and Latapie, H. and Imani, M.",
TITLE = "VLTP: Vision-Language Guided Token Pruning for Task-Oriented
Segmentation",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "9353-9363",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234646"}
@inproceedings{bb239730,
AUTHOR = "Ali, E. and Silva, S. and Khan, M.H.",
TITLE = "DPA: Dual Prototypes Alignment for Unsupervised Adaptation of
Vision-Language Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6083-6093",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234647"}
@inproceedings{bb239731,
AUTHOR = "Zhang, C. and Stepputtis, S. and Sycara, K. and Xie, Y.Q.",
TITLE = "Enhancing Vision-Language Few-Shot Adaptation with Negative Learning",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5905-5915",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234648"}
@inproceedings{bb239732,
AUTHOR = "Yamada, M. and Dharamshi, N. and Kohli, A. and Kasu, P. and Khan, A. and Ghulyani, M.",
TITLE = "Unleashing Potentials of Vision-Language Models for Zero-Shot HOI
Detection",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5751-5760",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234649"}
@inproceedings{bb239733,
AUTHOR = "Imam, R. and Gani, H. and Huzaifa, M. and Nandakumar, K.",
TITLE = "Test-Time Low Rank Adaptation via Confidence Maximization for
Zero-Shot Generalization of Vision-Language Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5449-5459",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234650"}
@inproceedings{bb239734,
AUTHOR = "Ghoddoosian, R. and Agarwal, N. and Dwivedi, I. and Darisuh, B.",
TITLE = "ACE: Action Concept Enhancement of Video-Language Models in
Procedural Videos",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "9521-9531",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234651"}
@inproceedings{bb239735,
AUTHOR = "Onoe, Y. and Rane, S. and Berger, Z. and Bitton, Y. and Cho, J. and Garg, R. and Ku, A. and Parekh, Z. and Pont Tuset, J. and Tanzer, G. and Wang, S. and Baldridge, J.",
TITLE = "DOCCI: Descriptions of Connected and Contrasting Images",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LX: 291-309",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234652"}
@inproceedings{bb239736,
AUTHOR = "Li, T. and Ma, M.M. and Peng, X.",
TITLE = "DEAL: Disentangle and Localize Concept-level Explanations for VLMs",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXXIX: 383-401",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234653"}
@inproceedings{bb239737,
AUTHOR = "Li, S.C. and Li, L. and Liu, Y. and Ren, S.H. and Liu, Y.X. and Gao, R.D. and Sun, X. and Hou, L.",
TITLE = "Vitatecs: A Diagnostic Dataset for Temporal Concept Understanding of
Video-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXX: 331-348",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234654"}
@inproceedings{bb239738,
AUTHOR = "Yang, Y.T. and Chen, M.H. and Qiu, Q. and Wu, J.H. and Wang, W.X. and Lin, B.B. and Guan, Z.Y. and He, X.F.",
TITLE = "Adapt2reward: Adapting Video-language Models to Generalizable Robotic
Rewards via Failure Prompts",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LVII: 163-180",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234655"}
@inproceedings{bb239739,
AUTHOR = "Rahmanzadehgervi, P. and Bolton, L. and Taesiri, M.R. and Nguyen, A.T.",
TITLE = "Vision Language Models are blind",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "V: 293-309",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234656"}
@inproceedings{bb239740,
AUTHOR = "Chytas, S.P. and Kim, H.W.J. and Singh, V.",
TITLE = "Understanding Multi-compositional Learning in Vision and Language
Models via Category Theory",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLVIII: 324-341",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234657"}
@inproceedings{bb239741,
AUTHOR = "Song, Y.Z. and Chen, Y.S. and Lin, T.L. and Liu, B. and Fu, J.L. and Shuai, H.H.",
TITLE = "Capture Concept Through Comparison: Vision-and-language Representation
Learning with Intrinsic Information Mining",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "III: 220-238",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234658"}
@inproceedings{bb239742,
AUTHOR = "Adhikari, R. and Thapaliya, S. and Dhakal, M. and Khanal, B.",
TITLE = "Tunevlseg: Prompt Tuning Benchmark for Vision-language Segmentation
Models",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "III: 44-62",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234659"}
@inproceedings{bb239743,
AUTHOR = "He, H.C. and Liu, W.B. and Xing, W.W.",
TITLE = "Biefficient: Bidirectionally Prompting Vision-language Models for
Parameter-efficient Video Recognition",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "III: 257-274",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234660"}
@inproceedings{bb239744,
AUTHOR = "Yang, J.K. and Dong, Y.H. and Liu, S. and Li, B. and Wang, Z.Y. and Tan, H.R. and Jiang, C.C. and Kang, J. and Zhang, Y.H. and Zhou, K.Y. and Liu, Z.W.",
TITLE = "Octopus: Embodied Vision-language Programmer from Environmental
Feedback",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "I: 20-38",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234661"}
@inproceedings{bb239745,
AUTHOR = "Kar, O.F. and Tonioni, A. and Poklukar, P. and Kulshrestha, A. and Zamir, A. and Tombari, F.",
TITLE = "Brave: Broadening the Visual Encoding of Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVI: 113-132",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234662"}
@inproceedings{bb239746,
AUTHOR = "Kamath, A. and Hsieh, C.Y. and Chang, K.W. and Krishna, R.",
TITLE = "The Hard Positive Truth About Vision-language Compositionality",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIV: 37-54",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234663"}
@inproceedings{bb239747,
AUTHOR = "Jia, B.X. and Chen, Y.X. and Yu, H.Y. and Wang, Y. and Niu, X.S. and Liu, T.Y. and Li, Q. and Huang, S.Y.",
TITLE = "Sceneverse: Scaling 3d Vision-language Learning for Grounded Scene
Understanding",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "IX: 289-310",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234664"}
@inproceedings{bb239748,
AUTHOR = "Zhang, Y.F. and Jiang, M. and Zhao, Q.",
TITLE = "Learning Chain of Counterfactual Thought for Bias-robust
Vision-language Reasoning",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "VIII: 334-351",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234665"}
@inproceedings{bb239749,
AUTHOR = "Li, J. and Chen, D. and Cai, T. and Chen, P.H. and Hong, Y. and Chen, Z.F. and Shen, Y.K. and Gan, C.",
TITLE = "Flexattention for Efficient High-resolution Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXV: 286-302",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234666"}
@inproceedings{bb239750,
AUTHOR = "Li, X. and Ding, J. and Chen, Z.Y. and Elhoseiny, M.",
TITLE = "UNI3DL: A Unified Model for 3d Vision-language Understanding",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXIII: 74-92",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234667"}
@inproceedings{bb239751,
AUTHOR = "Hao, T.X. and Ding, X.H. and Feng, J.X. and Yang, Y.H. and Chen, H. and Ding, G.",
TITLE = "Quantized Prompt for Efficient Generalization of Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIX: 54-73",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234668"}
@inproceedings{bb239752,
AUTHOR = "Xu, H.B. and Ke, X. and Li, Y.Z. and Xu, R. and Wu, H.Q. and Lin, X.F. and Guo, W.Z.",
TITLE = "Vision-language Action Knowledge Learning for Semantic-aware Action
Quality Assessment",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLII: 423-440",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234669"}
@inproceedings{bb239753,
AUTHOR = "Zhu, Z.Y. and Zhang, Z. and Ma, X.J. and Niu, X.S. and Chen, Y.X. and Jia, B.X. and Deng, Z.D. and Huang, S.Y. and Li, Q.",
TITLE = "Unifying 3d Vision-language Understanding via Promptable Queries",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLIV: 188-206",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234670"}
@inproceedings{bb239754,
AUTHOR = "Zhang, J.M. and Ma, X.J. and Wang, X. and Qiu, L.Y. and Wang, J.Q. and Jiang, Y.G. and Sang, J.",
TITLE = "Adversarial Prompt Tuning for Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLV: 56-72",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234671"}
@inproceedings{bb239755,
AUTHOR = "Wu, G. and Zhang, X. and Li, Z. and Chen, Z.W. and Liang, J.J. and Yang, J. and Li, X.",
TITLE = "Cascade Prompt Learning for Vision-language Model Adaptation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "L: 304-321",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234672"}
@inproceedings{bb239756,
AUTHOR = "Gao, S. and Jia, X.J. and Ren, X.H. and Tsang, I. and Guo, Q.",
TITLE = "Boosting Transferability in Vision-language Attacks via Diversification
Along the Intersection Region of Adversarial Trajectory",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LVII: 442-460",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234673"}
@inproceedings{bb239757,
AUTHOR = "Jiang, H.B. and Yue, J.P. and Luo, H. and Ding, Z. and Lu, Z.Q.",
TITLE = "Reinforcement Learning Friendly Vision-language Model for Minecraft",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXVIII: 1-17",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234674"}
@inproceedings{bb239758,
AUTHOR = "Nguyen, A.T. and Tai, K.S. and Chen, B.C. and Shukla, S.N. and Yu, H.C. and Torr, P.H.S. and Tian, T.P. and Lim, S.N.",
TITLE = "ucap: An Unsupervised Prompting Method for Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXIV: 425-439",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234675"}
@inproceedings{bb239759,
AUTHOR = "Zhang, Y. and Yu, K. and Wu, S.Q. and He, Z.H.",
TITLE = "Conceptual Codebook Learning for Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXVII: 235-251",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234676"}
@inproceedings{bb239760,
AUTHOR = "Chatterjee, A. and Luo, Y.R. and Gokhale, T. and Yang, Y.Z. and Baral, C.",
TITLE = "Revision: Rendering Tools Enable Spatial Fidelity in Vision-language
Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXX: 339-357",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234677"}
@inproceedings{bb239761,
AUTHOR = "Sharma, P. and Shaham, T.R. and Baradad, M. and Rodriiuez Munoz, A. and Duggal, S. and Isola, P. and Torralba, A. and Fu, S.",
TITLE = "A Vision Check-up for Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14410-14419",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234678"}
@inproceedings{bb239762,
AUTHOR = "Parodi, F. and Matelsky, J.K. and Regla Vargas, A. and Foglia, E.E. and Lim, C. and Weinberg, D. and Kording, K.P. and Herrick, H.M. and Platt, M.L.",
TITLE = "Vision-language models for decoding provider attention during
neonatal resuscitation",
BOOKTITLE = CVPM24,
YEAR = "2024",
PAGES = "343-353",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234679"}
@inproceedings{bb239763,
AUTHOR = "Zhang, Y.B. and Zhu, W.J. and Tang, H. and Ma, Z.Y. and Zhou, K.Y. and Zhang, L.",
TITLE = "Dual Memory Networks: A Versatile Adaptation Approach for
Vision-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "28718-28728",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234680"}
@inproceedings{bb239764,
AUTHOR = "Guo, Y.C. and Gu, X.D.",
TITLE = "JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language
Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "28695-28705",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234681"}
@inproceedings{bb239765,
AUTHOR = "Han, J. and Lin, Z.W. and Sun, Z.Y. and Gao, Y.G. and Yan, K. and Ding, S.H. and Gao, Y. and Xia, G.S.",
TITLE = "Anchor-based Robust Finetuning of Vision-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "26909-26918",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234682"}
@inproceedings{bb239766,
AUTHOR = "Cao, Q.L. and Zheng Qin, X. and Chen, Y.T. and Chao, M. and Yang, X.K.",
TITLE = "Domain Prompt Learning with Quaternion Networks",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "26627-26636",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234683"}
@inproceedings{bb239767,
AUTHOR = "Li, L. and Guan, H.Y. and Qiu, J.N. and Spratling, M.",
TITLE = "One Prompt Word is Enough to Boost Adversarial Robustness for
Pre-Trained Vision-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "24408-24419",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234684"}
@inproceedings{bb239768,
AUTHOR = "Zanella, M. and Fuchs, C. and de Vleeschouwer, C. and Ayed, I.B.",
TITLE = "Realistic Test-Time Adaptation of Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "25103-25112",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234685"}
@inproceedings{bb239769,
AUTHOR = "Fuchs, C. and Zanella, M. and de Vleeschouwer, C.",
TITLE = "Online Gaussian Test-Time Adaptation of Vision-Language Models",
BOOKTITLE = "MULA25",
YEAR = "2025",
PAGES = "128-137",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234686"}
@inproceedings{bb239770,
AUTHOR = "Zanella, M. and Ayed, I.B.",
TITLE = "On the Test-Time Zero-Shot Generalization of Vision-Language Models:
Do we Really need Prompt Learning?",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "23783-23793",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234687"}
@inproceedings{bb239771,
AUTHOR = "Yang, S. and Tian, Z. and Jiang, L. and Jia, J.Y.",
TITLE = "Unified Language-Driven Zero-Shot Domain Adaptation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "23407-23415",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234688"}
@inproceedings{bb239772,
AUTHOR = "Cui, J.Q. and Zhu, B. and Wen, X. and Qi, X.J. and Yu, B. and Zhang, H.W.",
TITLE = "Classes Are Not Equal: An Empirical Study on Image Recognition
Fairness",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "23283-23292",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234689"}
@inproceedings{bb239773,
AUTHOR = "Stojnic, V. and Kalantidis, Y. and Tolias, G.",
TITLE = "Label Propagation for Zero-shot Classification with Vision-Language
Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "23209-23218",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234690"}
@inproceedings{bb239774,
AUTHOR = "Yuan, T. and Zhang, X. and Liu, K. and Liu, B. and Chen, C. and Jin, J. and Jiao, Z.Z.",
TITLE = "Towards Surveillance Video-and-Language Understanding: New Dataset,
Baselines, and Challenges",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "22052-22061",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234691"}
@inproceedings{bb239775,
AUTHOR = "Chen, Y.F. and Chen, D.P. and Liu, R.J. and Zhou, S. and Xue, W.Y. and Peng, W.",
TITLE = "Align Before Adapt: Leveraging Entity-to-Region Alignments for
Generalizable Video Action Recognition",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18688-18698",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234692"}
@inproceedings{bb239776,
AUTHOR = "Mittal, H. and Agarwal, N. and Lo, S.Y. and Lee, K.",
TITLE = "Can't make an Omelette without Breaking some Eggs: Plausible Action
Anticipation using Large Video-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18580-18590",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234693"}
@inproceedings{bb239777,
AUTHOR = "Kahatapitiya, K. and Arnab, A. and Nagran, A. and Ryoo, M.S.",
TITLE = "VicTR: Video-conditioned Text Representations for Activity
Recognition",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18547-18558",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234694"}
@inproceedings{bb239778,
AUTHOR = "Wu, T.Y. and Ho, C.H. and Vasconcelos, N.M.",
TITLE = "ProTeCt: Prompt Tuning for Taxonomic Open Set Classification",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16531-16540",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234695"}
@inproceedings{bb239779,
AUTHOR = "Zhao, G. and Li, G.B. and Chen, W. and Yu, Y.Z.",
TITLE = "OVER-NAV: Elevating Iterative Vision-and-Language Navigation with
Open-Vocabulary Detection and StructurEd Representation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16296-16306",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234696"}
@inproceedings{bb239780,
AUTHOR = "Li, X. and Wu, Y.F. and Jiang, X.H. and Guo, Z.H. and Gong, M.M. and Cao, H.Y. and Liu, Y.S. and Jiang, D.Q. and Sun, X.",
TITLE = "Enhancing Visual Document Understanding with Contrastive Learning in
Large Visual-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "15546-15555",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234697"}
@inproceedings{bb239781,
AUTHOR = "Pham, K. and Huynh, C. and Lim, S.N. and Shrivastava, A.",
TITLE = "Composing Object Relations and Attributes for Image-Text Matching",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14354-14363",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234698"}
@inproceedings{bb239782,
AUTHOR = "Xu, Z.L. and Zhu, Y. and Deng, S.Q. and Mittal, A. and Chen, Y.B. and Wang, M. and Favaro, P. and Tighe, J. and Modolo, D.",
TITLE = "Benchmarking Zero-Shot Recognition with Vision-Language Models:
Challenges on Granularity and Specificity",
BOOKTITLE = WhatNext24,
YEAR = "2024",
PAGES = "1827-1836",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234699"}
@inproceedings{bb239783,
AUTHOR = "Luo, Z.W. and Gustafsson, F.K. and Zhao, Z. and Sjolund, J. and Schon, T.B.",
TITLE = "Photo-Realistic Image Restoration in the Wild with Controlled
Vision-Language Models",
BOOKTITLE = NTIRE24,
YEAR = "2024",
PAGES = "6641-6651",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234700"}
@inproceedings{bb239784,
AUTHOR = "Huang, C.Q. and Jiang, A. and Feng, J.H. and Zhang, Y. and Wang, X.C. and Wang, Y.F.",
TITLE = "Adapting Visual-Language Models for Generalizable Anomaly Detection
in Medical Images",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "11375-11385",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234701"}
@inproceedings{bb239785,
AUTHOR = "Bang, J. and Ahn, S. and Lee, J.G.",
TITLE = "Active Prompt Learning in Vision Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "26994-27004",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234702"}
@inproceedings{bb239786,
AUTHOR = "Pan, C. and Yaman, B. and Nesti, T. and Mallik, A. and Allievi, A.G. and Velipasalar, S. and Ren, L.",
TITLE = "VLP: Vision Language Planning for Autonomous Driving",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14760-14769",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234703"}
@inproceedings{bb239787,
AUTHOR = "Liang, M. and Su, J.C. and Schulter, S. and Garg, S. and Zhao, S.Y. and Wu, Y. and Chandraker, M.",
TITLE = "AIDE: An Automatic Data Engine for Object Detection in Autonomous
Driving",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14695-14706",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234704"}
@inproceedings{bb239788,
AUTHOR = "Li, Z. and Li, X. and Fu, X. and Zhang, X. and Wang, W.Q. and Chen, S. and Yang, J.",
TITLE = "PromptKD: Unsupervised Prompt Distillation for Vision-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "26607-26616",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234705"}
@inproceedings{bb239789,
AUTHOR = "Khandelwal, A.",
TITLE = "PromptSync: Bridging Domain Gaps in Vision-Language Models through
Class-Aware Prototype Alignment and Discrimination",
BOOKTITLE = ZeroShot24,
YEAR = "2024",
PAGES = "7819-7828",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234706"}
@inproceedings{bb239790,
AUTHOR = "Hirohashi, Y. and Hirakawa, T. and Yamashita, T. and Fujiyoshi, H.",
TITLE = "Prompt Learning with One-Shot Setting based Feature Space Analysis in
Vision-and-Language Models",
BOOKTITLE = ZeroShot24,
YEAR = "2024",
PAGES = "7761-7770",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234707"}
@inproceedings{bb239791,
AUTHOR = "Zhang, L. and Awal, R. and Agrawal, A.",
TITLE = "Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to
Enhance Visio-Linguistic Compositional Understanding",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13774-13784",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234708"}
@inproceedings{bb239792,
AUTHOR = "Rosasco, A. and Berti, S. and Pasquale, G. and Malafronte, D. and Sato, S. and Segawa, H. and Inada, T. and Natale, L.",
TITLE = "ConCon-Chi: Concept-Context Chimera Benchmark for Personalized
Vision-Language Tasks",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "22239-22248",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234709"}
@inproceedings{bb239793,
AUTHOR = "Cheng, S. and Guo, Z.C. and Wu, J. and Fang, K. and Li, P. and Liu, H.P. and Liu, Y.",
TITLE = "EgoThink: Evaluating First-Person Perspective Thinking Capability of
Vision-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14291-14302",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234710"}
@inproceedings{bb239794,
AUTHOR = "Kil, J. and Song, C.H. and Zheng, B. and Deng, X. and Su, Y. and Chao, W.L.",
TITLE = "Dual-View Visual Contextualization for Web Navigation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14445-14454",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234711"}
@inproceedings{bb239795,
AUTHOR = "Guo, Y.Y. and Wang, G.Z. and Kankanhalli, M.",
TITLE = "PELA: Learning Parameter-Efficient Models with Low-Rank Approximation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "15699-15709",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234712"}
@inproceedings{bb239796,
AUTHOR = "Farina, M. and Mancini, M. and Cunegatti, E. and Cunegatti, E. and Iacca, G. and Ricci, E.",
TITLE = "MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16185-16195",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234713"}
@inproceedings{bb239797,
AUTHOR = "Mu, F.Z. and Mo, S.C. and Li, Y.",
TITLE = "SnAG: Scalable and Accurate Video Grounding",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18930-18940",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234714"}
@inproceedings{bb239798,
AUTHOR = "Cao, Y.H. and Ji, K.X. and Huang, Z.Y. and Zheng, C.Y. and Liu, J.J. and Wang, J. and Chen, J.D. and Yang, M.",
TITLE = "Towards Better Vision-Inspired Vision-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13537-13547",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234715"}
@inproceedings{bb239799,
AUTHOR = "Shi, K.Y. and Dong, Q. and Goncalves, L. and Tu, Z.W. and Soatto, S.",
TITLE = "Non-autoregressive Sequence-to-Sequence Vision-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13603-13612",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT234716"}
Last update:Jan 23, 2026 at 20:54:10