{"list":"other","total":71,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2403.20330","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","created":"2024-03-29","cited_by_count":914},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"2311.16922","title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","created":"2023-11-28","cited_by_count":688},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317},{"id":"2309.01431","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","created":"2023-09-04","cited_by_count":312},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229},{"id":"1606.05386","title":"Model-Agnostic Interpretability of Machine Learning","created":"2016-06-16","cited_by_count":219},{"id":"1604.00825","title":"Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers","created":"2016-04-04","cited_by_count":199},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169},{"id":"1904.04357","title":"Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering","created":"2019-04-08","cited_by_count":146},{"id":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135},{"id":"2203.12221","title":"Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)","created":"2022-03-23","cited_by_count":122},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104},{"id":"1803.10906","title":"Motion-Appearance Co-Memory Networks for Video Question Answering","created":"2018-03-29","cited_by_count":95},{"id":"2202.05306","title":"Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks","created":"2022-02-10","cited_by_count":95},{"id":"2406.11839","title":"mDPO: Conditional Preference Optimization for Multimodal Large Language Models","created":"2024-06-17","cited_by_count":92},{"id":"2503.02199","title":"Words or Vision: Do Vision-Language Models Have Blind Faith in Text?","created":"2025-03-04","cited_by_count":89},{"id":"2105.04857","title":"Leveraging Sparse Linear Layers for Debuggable Deep Networks","created":"2021-05-11","cited_by_count":82},{"id":"2008.09105","title":"Location-aware Graph Convolutional Networks for Video Question Answering","created":"2020-08-07","cited_by_count":80},{"id":"2404.14233","title":"Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback","created":"2024-04-22","cited_by_count":80},{"id":"2403.08730","title":"Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization","created":"2024-03-13","cited_by_count":75},{"id":"2109.04448","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","created":"2021-09-09","cited_by_count":72},{"id":"2405.19716","title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","created":"2024-05-30","cited_by_count":70},{"id":"2407.06192","title":"Multi-Object Hallucination in Vision-Language Models","created":"2024-07-08","cited_by_count":60},{"id":"2104.14085","title":"Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering","created":"2021-04-29","cited_by_count":56},{"id":"2012.05710","title":"Look Before you Speak: Visually Contextualized Utterances","created":"2020-12-10","cited_by_count":53},{"id":"2203.17247","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","created":"2022-03-30","cited_by_count":53},{"id":"2212.08158","title":"MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks","created":"2022-12-15","cited_by_count":43},{"id":"2407.10114","title":"TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation","created":"2024-07-14","cited_by_count":42},{"id":"1707.06355","title":"Video Question Answering via Attribute-Augmented Attention Network Learning","created":"2017-07-20","cited_by_count":39},{"id":"2403.18346","title":"Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective","created":"2024-03-27","cited_by_count":39},{"id":"2007.02036","title":"Modality Shifting Attention Network for Multi-modal Video Question Answering","created":"2020-07-04","cited_by_count":38},{"id":"2110.14375","title":"Perceptual Score: What Data Modalities Does Your Model Perceive?","created":"2021-10-27","cited_by_count":35},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35},{"id":"2203.02013","title":"DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations","created":"2022-03-03","cited_by_count":34},{"id":"2009.08043","title":"Self-supervised pre-training and contrastive representation learning for multiple-choice video QA","created":"2020-09-17","cited_by_count":28},{"id":"2404.18624","title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?","created":"2024-04-29","cited_by_count":24},{"id":"2408.12763","title":"Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models","created":"2024-08-22","cited_by_count":23},{"id":"2402.06244","title":"Quantifying and Enhancing Multi-modal Robustness with Modality Preference","created":"2024-02-09","cited_by_count":16},{"id":"2309.14118","title":"MultiModN- Multimodal, Multi-Task, Interpretable Modular Networks","created":"2023-09-25","cited_by_count":14},{"id":"2503.06670","title":"Attention, Please! PixelSHAP Reveals What Vision-Language Models Actually Focus On","created":"2025-03-09","cited_by_count":9},{"id":"2104.05166","title":"Object-Centric Representation Learning for Video Question Answering","created":"2021-04-12","cited_by_count":7},{"id":"2305.07132","title":"Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization","created":"2023-05-11","cited_by_count":5},{"id":"2011.12372","title":"Play Fair: Frame Attributions in Video Models","created":"2020-11-24","cited_by_count":4},{"id":"2204.11929","title":"Temporal Relevance Analysis for Video Action Models","created":"2022-04-25","cited_by_count":1}],"next_cursor":null}