{"list":"other","total":63,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"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":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","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":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267},{"id":"2311.18445","title":"VTimeLLM: Empower LLM to Grasp Video Moments","created":"2023-11-30","cited_by_count":255},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197},{"id":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133},{"id":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104},{"id":"2305.02677","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","created":"2023-05-04","cited_by_count":99},{"id":"2306.08640","title":"AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn","created":"2023-06-14","cited_by_count":97},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84},{"id":"2207.10883","title":"My View is the Best View: Procedure Learning from Egocentric Videos","created":"2022-07-22","cited_by_count":81},{"id":"2304.12301","title":"AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation","created":"2023-04-24","cited_by_count":64},{"id":"2401.02582","title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","created":"2024-01-05","cited_by_count":56},{"id":"1901.01874","title":"Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions","created":"2019-01-07","cited_by_count":54},{"id":"2110.01770","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","created":"2021-10-05","cited_by_count":53},{"id":"2310.00582","title":"Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs","created":"2023-10-01","cited_by_count":47},{"id":"2404.12353","title":"V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning","created":"2024-04-18","cited_by_count":46},{"id":"1612.07796","title":"First-Person Activity Forecasting with Online Inverse Reinforcement Learning","created":"2016-12-22","cited_by_count":40},{"id":"1912.08077","title":"Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition","created":"2019-12-15","cited_by_count":35},{"id":"2209.09484","title":"Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos","created":"2022-09-20","cited_by_count":35},{"id":"2307.08243","title":"Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting","created":"2023-07-17","cited_by_count":34},{"id":"2301.01380","title":"Ego-Only: Egocentric Action Detection without Exocentric Transferring","created":"2023-01-03","cited_by_count":31},{"id":"2307.07483","title":"Multimodal Distillation for Egocentric Action Recognition","created":"2023-07-14","cited_by_count":28},{"id":"2212.06969","title":"EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries","created":"2022-12-14","cited_by_count":25},{"id":"2211.10528","title":"Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization","created":"2022-11-18","cited_by_count":24},{"id":"1909.06761","title":"Multitask Learning to Improve Egocentric Action Recognition","created":"2019-09-15","cited_by_count":23},{"id":"2303.08345","title":"Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos","created":"2023-03-15","cited_by_count":23},{"id":"2303.16024","title":"Egocentric Auditory Attention Localization in Conversations","created":"2023-03-28","cited_by_count":18},{"id":"2309.02423","title":"EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding","created":"2023-09-05","cited_by_count":15},{"id":"2305.13777","title":"VisorGPT: Learning Visual Prior via Generative Pre-Training","created":"2023-05-23","cited_by_count":11},{"id":"2209.12164","title":"Multi-modal Segment Assemblage Network for Ad Video Editing with Importance-Coherence Reward","created":"2022-09-25","cited_by_count":10},{"id":"2310.11699","title":"MISAR: A Multimodal Instructional System with Augmented Reality","created":"2023-10-18","cited_by_count":10},{"id":"2306.10354","title":"LLMVA-GEBC: Large Language Model with Video Adapter for Generic Event Boundary Captioning","created":"2023-06-17","cited_by_count":9}],"next_cursor":null}