{"total":62,"rows":[{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252,"area":"lr"},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203,"area":null},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184,"area":"lr"},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169,"area":null},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153,"area":"lr"},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133,"area":null},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126,"area":null},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117,"area":null},{"id":"2106.04632","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","created":"2021-06-08","cited_by_count":95,"area":null},{"id":"2106.00245","title":"Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models","created":"2021-06-01","cited_by_count":75,"area":null},{"id":"2107.09609","title":"QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries","created":"2021-07-20","cited_by_count":72,"area":null},{"id":"2212.05136","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","created":"2022-12-09","cited_by_count":67,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"area":null},{"id":"2207.12647","title":"Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering","created":"2022-07-26","cited_by_count":57,"area":"lr"},{"id":"2310.15747","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","created":"2023-10-24","cited_by_count":51,"area":"lr"},{"id":"2202.04800","title":"The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning","created":"2022-02-10","cited_by_count":38,"area":"lr"},{"id":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2106.11988","title":"On the Diversity and Limits of Human Explanations","created":"2021-06-22","cited_by_count":30,"area":null},{"id":"2203.14040","title":"Visual Abductive Reasoning","created":"2022-03-26","cited_by_count":30,"area":"lr"},{"id":"2311.07022","title":"ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models","created":"2023-11-13","cited_by_count":26,"area":null},{"id":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","cited_by_count":26,"area":null},{"id":"2312.08367","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","created":"2023-12-13","cited_by_count":23,"area":null},{"id":"2207.12576","title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","created":"2022-07-25","cited_by_count":20,"area":"lr"},{"id":"2501.01426","title":"Unifying Specialized Visual Encoders for Video Language Models","created":"2025-01-02","cited_by_count":10,"area":"lr"},{"id":"2208.03812","title":"When can I Speak? Predicting initiation points for spoken dialogue agents","created":"2022-08-07","cited_by_count":9,"area":null},{"id":"2406.09646","title":"A Survey of Video Datasets for Grounded Event Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2511.16669","title":"Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO","created":"2025-11-20","cited_by_count":9,"area":"lr"},{"id":"2105.07122","title":"Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues","created":"2021-05-15","cited_by_count":8,"area":null},{"id":"2311.01620","title":"ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2310.14670","title":"Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2601.13836","title":"FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs","created":"2026-01-20","cited_by_count":7,"area":"mllm"},{"id":"2303.06067","title":"Modeling Events and Interactions through Temporal Processes -- A Survey","created":"2023-03-10","cited_by_count":6,"area":null},{"id":"2402.03284","title":"Deal, or no deal (or who knows)? Forecasting Uncertainty in Conversations using Large Language Models","created":"2024-02-05","cited_by_count":6,"area":null},{"id":"2410.02768","title":"Uncertainty-Guided Self-Questioning and Answering for Video-Language Alignment","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2305.13903","title":"Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought","created":"2023-05-23","cited_by_count":5,"area":"lr"},{"id":"2511.20272","title":"VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs","created":"2025-11-25","cited_by_count":5,"area":"mllm"},{"id":"2212.06971","title":"Find Someone Who: Visual Commonsense Understanding in Human-Centric Grounding","created":"2022-12-14","cited_by_count":4,"area":null},{"id":"2312.17429","title":"Commonsense for Zero-Shot Natural Language Video Localization","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2502.19409","title":"ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Models","created":"2025-02-26","cited_by_count":4,"area":"lr"},{"id":"2203.10249","title":"Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue Comprehension","created":"2022-03-19","cited_by_count":3,"area":null},{"id":"2412.03567","title":"Streaming Detection of Queried Event Start","created":"2024-12-04","cited_by_count":3,"area":null},{"id":"2110.06476","title":"Winning the ICCV'2021 VALUE Challenge: Task-aware Ensemble and Transfer Learning with Visual Concepts","created":"2021-10-13","cited_by_count":2,"area":null},{"id":"2207.09083","title":"Relational Future Captioning Model for Explaining Likely Collisions in Daily Tasks","created":"2022-07-19","cited_by_count":2,"area":null},{"id":"2210.03941","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2304.02313","title":"Personality-aware Human-centric Multimodal Reasoning: A New Task, Dataset and Baselines","created":"2023-04-05","cited_by_count":2,"area":"lr"},{"id":"2304.08083","title":"VCD: Visual Causality Discovery for Cross-Modal Question Reasoning","created":"2023-04-17","cited_by_count":2,"area":null},{"id":"2404.13530","title":"Listen Then See: Video Alignment with Speaker Attention","created":"2024-04-21","cited_by_count":2,"area":null},{"id":"2412.19304","title":"Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries","created":"2024-12-26","cited_by_count":2,"area":"lr"},{"id":"2503.15807","title":"Video-VoT-R1: An efficient video inference model integrating image packing and AoE architecture","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2304.10505","title":"Video Pre-trained Transformer: A Multimodal Mixture of Pre-trained Experts","created":"2023-03-24","cited_by_count":1,"area":null},{"id":"2604.20460","title":"CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs","created":"2026-04-22","cited_by_count":1,"area":"mllm"},{"id":"2608.08820","title":"LogiShot: Logically Coherent Cross-Shot Video Generation","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2203.12344","title":"How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs","created":"2022-03-23","cited_by_count":0,"area":null},{"id":"2204.13548","title":"Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2301.03410","title":"In Defense of Structural Symbolic Representation for Video Event-Relation Prediction","created":"2023-01-06","cited_by_count":0,"area":null},{"id":"2311.16311","title":"Characterizing Video Question Answering with Sparsified Inputs","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2504.05463","title":"REVEAL: Relation-based Video Representation Learning for Video-Question-Answering","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2511.08348","title":"VideoChain: A Transformer-Based Framework for Multi-hop Video Question Generation","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2605.31069","title":"Towards Effective Long-Video Event Prediction via Multi-Level Event Semantics Mining","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2608.30716","title":"SocialReasonBench: A Video-QA Benchmark for Social Reasoning with Counterfactual Narrative Videos","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}