{"total":151,"rows":[{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857,"area":null},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"area":null},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497,"area":null},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447,"area":null},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407,"area":null},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347,"area":null},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343,"area":null},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"area":null},{"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":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199,"area":null},{"id":"2205.12005","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","created":"2022-05-24","cited_by_count":187,"area":null},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171,"area":null},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"area":null},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147,"area":null},{"id":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2112.01522","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","created":"2021-12-02","cited_by_count":125,"area":null},{"id":"2305.11176","title":"Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model","created":"2023-05-18","cited_by_count":116,"area":null},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87,"area":null},{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83,"area":null},{"id":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74,"area":null},{"id":"2209.06430","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","created":"2022-09-14","cited_by_count":74,"area":null},{"id":"2206.07160","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","created":"2022-06-14","cited_by_count":73,"area":null},{"id":"2212.14546","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","created":"2022-12-30","cited_by_count":72,"area":null},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71,"area":null},{"id":"2212.04979","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","created":"2022-12-09","cited_by_count":70,"area":null},{"id":"2208.02131","title":"Masked Vision and Language Modeling for Multi-modal Representation Learning","created":"2022-08-03","cited_by_count":67,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63,"area":null},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57,"area":null},{"id":"2212.09522","title":"MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering","created":"2022-12-19","cited_by_count":55,"area":null},{"id":"2311.17404","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","created":"2023-11-29","cited_by_count":55,"area":null},{"id":"2303.15935","title":"When Brain-inspired AI Meets AGI","created":"2023-03-28","cited_by_count":54,"area":null},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51,"area":null},{"id":"2310.19060","title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","created":"2023-10-29","cited_by_count":49,"area":null},{"id":"2303.17839","title":"Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations","created":"2023-03-31","cited_by_count":46,"area":null},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2304.04227","title":"Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions","created":"2023-04-09","cited_by_count":42,"area":null},{"id":"2207.07885","title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","created":"2022-07-16","cited_by_count":41,"area":null},{"id":"2212.10368","title":"Masked Event Modeling: Self-Supervised Pretraining for Event Cameras","created":"2022-12-20","cited_by_count":41,"area":null},{"id":"2401.01505","title":"Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports","created":"2024-01-03","cited_by_count":41,"area":null},{"id":"2403.13347","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","created":"2024-03-20","cited_by_count":41,"area":null},{"id":"2311.13627","title":"Vamos: Versatile Action Models for Video Understanding","created":"2023-11-22","cited_by_count":40,"area":null},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35,"area":null},{"id":"2303.11403","title":"eP-ALM: Efficient Perceptual Augmentation of Language Models","created":"2023-03-20","cited_by_count":34,"area":null},{"id":"2312.07395","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2302.13668","title":"Contrastive Video Question Answering via Video Graph Transformer","created":"2023-02-27","cited_by_count":32,"area":null},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32,"area":null},{"id":"2211.08887","title":"Stare at What You See: Masked Image Modeling without Reconstruction","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"area":null},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29,"area":null},{"id":"2408.06687","title":"Masked Image Modeling: A Survey","created":"2024-08-13","cited_by_count":29,"area":null},{"id":"2305.13631","title":"EDIS: Entity-Driven Image Search over Multimodal Web Content","created":"2023-05-23","cited_by_count":27,"area":null},{"id":"2306.11732","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","created":"2023-06-15","cited_by_count":27,"area":null},{"id":"2502.03814","title":"Large Language Models for Multi-Robot Systems: A Survey","created":"2025-02-06","cited_by_count":27,"area":null},{"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":"2303.16839","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","created":"2023-03-29","cited_by_count":24,"area":null},{"id":"2305.08381","title":"Parameter-efficient Tuning of Large-scale Multimodal Foundation Model","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2212.03490","title":"SimVTP: Simple Video Text Pre-training with Masked Autoencoders","created":"2022-12-07","cited_by_count":21,"area":null},{"id":"2307.12058","title":"Discovering Spatio-Temporal Rationales for Video Question Answering","created":"2023-07-22","cited_by_count":21,"area":null},{"id":"2403.08755","title":"DAM: Dynamic Adapter Merging for Continual Video QA Learning","created":"2024-03-13","cited_by_count":19,"area":null},{"id":"2305.13167","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2203.13371","title":"FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2211.11446","title":"SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training","created":"2022-11-21","cited_by_count":15,"area":null},{"id":"2303.13009","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","created":"2023-03-23","cited_by_count":15,"area":null},{"id":"2305.02519","title":"ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos","created":"2023-05-04","cited_by_count":15,"area":null},{"id":"2308.11551","title":"Multi-event Video-Text Retrieval","created":"2023-08-22","cited_by_count":15,"area":null},{"id":"2311.05698","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","created":"2023-11-09","cited_by_count":15,"area":null},{"id":"2305.14173","title":"TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2304.07647","title":"LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision","created":"2023-04-15","cited_by_count":13,"area":null},{"id":"2412.19178","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","created":"2024-12-26","cited_by_count":13,"area":null},{"id":"2301.07463","title":"Temporal Perceiving Video-Language Pre-training","created":"2023-01-18","cited_by_count":12,"area":null},{"id":"2409.04732","title":"VidLPRO: A $\\underline{Vid}$eo-$\\underline{L}$anguage $\\underline{P}$re-training Framework for $\\underline{Ro}$botic and Laparoscopic Surgery","created":"2024-09-07","cited_by_count":12,"area":null},{"id":"2212.00986","title":"Masked Contrastive Pre-Training for Efficient Video-Text Retrieval","created":"2022-12-02","cited_by_count":11,"area":null},{"id":"2304.08809","title":"SViTT: Temporal Learning of Sparse Video-Text Transformers","created":"2023-04-18","cited_by_count":11,"area":null},{"id":"2602.03589","title":"SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM","created":"2026-02-03","cited_by_count":11,"area":null},{"id":"2307.04231","title":"Mx2M: Masked Cross-Modality Modeling in Domain Adaptation for 3D Semantic Segmentation","created":"2023-07-09","cited_by_count":10,"area":null},{"id":"2412.17295","title":"Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding","created":"2024-12-23","cited_by_count":9,"area":null},{"id":"2506.07886","title":"EgoM2P: Egocentric Multimodal Multitask Pretraining","created":"2025-06-09","cited_by_count":9,"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":"2401.01529","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","created":"2024-01-03","cited_by_count":8,"area":null},{"id":"2407.03788","title":"MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2407.07478","title":"EA-VTR: Event-Aware Video-Text Retrieval","created":"2024-07-10","cited_by_count":8,"area":null},{"id":"2301.01953","title":"Learning Trajectory-Word Alignments for Video-Language Tasks","created":"2023-01-05","cited_by_count":7,"area":null},{"id":"2308.09363","title":"Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models","created":"2023-08-18","cited_by_count":7,"area":null},{"id":"2311.01233","title":"Long Story Short: a Summarize-then-Search Method for Long Video Question Answering","created":"2023-11-02","cited_by_count":7,"area":null},{"id":"2209.15280","title":"Learning Transferable Spatiotemporal Representations from Natural Script Knowledge","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2302.05016","title":"Is Multimodal Vision Supervision Beneficial to Language?","created":"2023-02-10","cited_by_count":6,"area":null},{"id":"2311.07285","title":"Multi Sentence Description of Complex Manipulation Action Videos","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2409.19865","title":"TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2412.06182","title":"Towards Long Video Understanding via Fine-detailed Video Story Generation","created":"2024-12-09","cited_by_count":6,"area":null}],"next_cursor":"100"}