{"list":"other","total":63,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"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":"2312.08914","title":"CogAgent: A Visual Language Model for GUI Agents","created":"2023-12-14","cited_by_count":704},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"2011.07231","title":"ActBERT: Learning Global-Local Video-Text Representations","created":"2020-11-14","cited_by_count":267},{"id":"2405.19209","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","created":"2024-05-29","cited_by_count":251},{"id":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2406.14515","title":"MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding","created":"2024-06-20","cited_by_count":182},{"id":"2410.07073","title":"Pixtral 12B","created":"2024-10-09","cited_by_count":179},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146},{"id":"2310.10634","title":"OpenAgents: An Open Platform for Language Agents in the Wild","created":"2023-10-16","cited_by_count":137},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114},{"id":"2112.00431","title":"MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions","created":"2021-12-01","cited_by_count":108},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105},{"id":"2402.04252","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","created":"2024-02-06","cited_by_count":99},{"id":"2406.09396","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","created":"2024-06-13","cited_by_count":68},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65},{"id":"2210.06031","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","created":"2022-10-12","cited_by_count":59},{"id":"2312.05269","title":"LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos","created":"2023-12-07","cited_by_count":51},{"id":"2402.05861","title":"Memory Consolidation Enables Long-Context Video Understanding","created":"2024-02-08","cited_by_count":45},{"id":"2410.19100","title":"VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks","created":"2024-10-24","cited_by_count":43},{"id":"2402.11550","title":"LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration","created":"2024-02-18","cited_by_count":38},{"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},{"id":"2312.11897","title":"Text-Conditioned Resampler For Long Form Video Understanding","created":"2023-12-19","cited_by_count":24},{"id":"2312.08367","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","created":"2023-12-13","cited_by_count":23},{"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}],"next_cursor":null}