{"list":"other","total":204,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"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":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"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":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"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":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"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":"2403.06764","title":"An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models","created":"2024-03-11","cited_by_count":642},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"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":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2403.15388","title":"LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models","created":"2024-03-22","cited_by_count":402},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2410.04417","title":"SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference","created":"2024-10-06","cited_by_count":391},{"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":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356},{"id":"2407.12772","title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","created":"2024-07-17","cited_by_count":353},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317},{"id":"2412.04467","title":"VisionZip: Longer is Better but Not Necessary in Vision Language Models","created":"2024-12-05","cited_by_count":313},{"id":"2410.17247","title":"PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction","created":"2024-10-22","cited_by_count":294},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290},{"id":"2006.16228","title":"Self-Supervised MultiModal Versatile Networks","created":"2020-06-29","cited_by_count":276},{"id":"2504.06958","title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","created":"2025-04-09","cited_by_count":255},{"id":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225},{"id":"2501.00574","title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","created":"2024-12-31","cited_by_count":220},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2409.14485","title":"Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding","created":"2024-09-22","cited_by_count":213},{"id":"2501.12386","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","created":"2025-01-21","cited_by_count":211},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167},{"id":"2502.21271","title":"Adaptive Keyframe Sampling for Long Video Understanding","created":"2025-02-28","cited_by_count":167},{"id":"2501.03895","title":"LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token","created":"2025-01-07","cited_by_count":166},{"id":"2409.12961","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","created":"2024-09-19","cited_by_count":159},{"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},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147},{"id":"2405.05803","title":"Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference","created":"2024-05-09","cited_by_count":139},{"id":"2402.12451","title":"The Revolution of Multimodal Large Language Models: A Survey","created":"2024-02-19","cited_by_count":137},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135},{"id":"1811.12432","title":"AdaFrame: Adaptive Frame Selection for Fast Video Recognition","created":"2018-11-29","cited_by_count":134},{"id":"2407.15841","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","created":"2024-07-22","cited_by_count":125},{"id":"2404.03413","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","created":"2024-04-04","cited_by_count":118},{"id":"2503.00540","title":"Streaming Video Question-Answering with In-context Video KV-Cache Retrieval","created":"2025-03-01","cited_by_count":117},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116},{"id":"2410.19702","title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning","created":"2024-10-25","cited_by_count":106},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102},{"id":"1511.06984","title":"End-to-end Learning of Action Detection from Frame Glimpses in Videos","created":"2015-11-22","cited_by_count":101},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98},{"id":"2504.17343","title":"TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos","created":"2025-04-24","cited_by_count":97},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96},{"id":"2405.10739","title":"Efficient Multimodal Large Language Models: A Survey","created":"2024-05-17","cited_by_count":96},{"id":"2411.15024","title":"DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models","created":"2024-11-22","cited_by_count":96},{"id":"2406.18139","title":"LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference","created":"2024-06-26","cited_by_count":95},{"id":"2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","created":"2023-09-21","cited_by_count":90},{"id":"2007.15796","title":"AR-Net: Adaptive Frame Resolution for Efficient Action Recognition","created":"2020-07-31","cited_by_count":88},{"id":"2502.19680","title":"M-LLM Based Video Frame Selection for Efficient Video Understanding","created":"2025-02-27","cited_by_count":88},{"id":"2410.03226","title":"Frame-Voyager: Learning to Query Frames for Video Large Language Models","created":"2024-10-04","cited_by_count":83},{"id":"2504.02259","title":"T*: Re-thinking Temporal Search for Long-Form Video Understanding","created":"2025-04-03","cited_by_count":82},{"id":"2506.23825","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","created":"2025-06-30","cited_by_count":81}],"next_cursor":"100"}