{"list":"other","total":80,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"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":"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":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"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":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"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":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"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":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"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":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2011.07231","title":"ActBERT: Learning Global-Local Video-Text Representations","created":"2020-11-14","cited_by_count":267},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267},{"id":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229},{"id":"2305.20088","title":"Improving CLIP Training with Language Rewrites","created":"2023-05-31","cited_by_count":217},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2007.10937","title":"MovieNet: A Holistic Dataset for Movie Understanding","created":"2020-07-21","cited_by_count":206},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178},{"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":"2402.11435","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","created":"2024-02-18","cited_by_count":122},{"id":"2307.15644","title":"Scaling Data Generation in Vision-and-Language Navigation","created":"2023-07-28","cited_by_count":117},{"id":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105},{"id":"2403.18406","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","created":"2024-03-27","cited_by_count":97},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91},{"id":"2204.02968","title":"Temporal Alignment Networks for Long-term Video","created":"2022-04-06","cited_by_count":84},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74},{"id":"2212.04979","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","created":"2022-12-09","cited_by_count":70},{"id":"2304.14407","title":"ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System","created":"2023-04-27","cited_by_count":65},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55},{"id":"2310.15747","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","created":"2023-10-24","cited_by_count":51},{"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":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42},{"id":"2311.13627","title":"Vamos: Versatile Action Models for Video Understanding","created":"2023-11-22","cited_by_count":40},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35},{"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":"2401.16702","title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","created":"2024-01-30","cited_by_count":34},{"id":"2401.08567","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","created":"2024-01-16","cited_by_count":27},{"id":"2211.09778","title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision","created":"2022-11-17","cited_by_count":26},{"id":"2403.16998","title":"Understanding Long Videos with Multimodal Language Models","created":"2024-03-25","cited_by_count":25},{"id":"2401.06129","title":"Distilling Vision-Language Models on Millions of Videos","created":"2024-01-11","cited_by_count":20}],"next_cursor":null}