{"list":"other","total":51,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"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":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"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":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"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":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251},{"id":"1812.07119","title":"Composing Text and Image for Image Retrieval - An Empirical Odyssey","created":"2018-12-18","cited_by_count":236},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2303.15247","title":"Zero-Shot Composed Image Retrieval with Textual Inversion","created":"2023-03-27","cited_by_count":176},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169},{"id":"2302.03084","title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","created":"2023-02-06","cited_by_count":156},{"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":"1708.01311","title":"Automatic Spatially-aware Fashion Concept Discovery","created":"2017-08-03","cited_by_count":134},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105},{"id":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103},{"id":"2303.11916","title":"CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion","created":"2023-03-21","cited_by_count":85},{"id":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83},{"id":"2310.05473","title":"Sentence-level Prompts Benefit Composed Image Retrieval","created":"2023-10-09","cited_by_count":59},{"id":"2006.11149","title":"Compositional Learning of Image-Text Query for Image Retrieval","created":"2020-06-19","cited_by_count":57},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57},{"id":"1709.01362","title":"Predicting Visual Features from Text for Image and Video Caption Retrieval","created":"2017-09-05","cited_by_count":53},{"id":"2308.14746","title":"CoVR-2: Automatic Data Construction for Composed Video Retrieval","created":"2023-08-28","cited_by_count":52},{"id":"2309.16137","title":"Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval","created":"2023-09-28","cited_by_count":52},{"id":"2306.07969","title":"GeneCIS: A Benchmark for General Conditional Image Similarity","created":"2023-06-13","cited_by_count":47},{"id":"1905.12794","title":"Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback","created":"2019-05-30","cited_by_count":43},{"id":"1609.08124","title":"Learning Language-Visual Embedding for Movie Understanding with Natural-Language","created":"2016-09-26","cited_by_count":41},{"id":"1909.04101","title":"Neural Naturalist: Generating Fine-Grained Image Comparisons","created":"2019-09-09","cited_by_count":36},{"id":"2306.07272","title":"Zero-shot Composed Text-Image Retrieval","created":"2023-06-12","cited_by_count":32},{"id":"2312.01998","title":"Language-only Efficient Training of Zero-shot Composed Image Retrieval","created":"2023-12-04","cited_by_count":27},{"id":"2403.16997","title":"Composed Video Retrieval via Enriched Context and Discriminative Embeddings","created":"2024-03-25","cited_by_count":26},{"id":"2312.08924","title":"Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking","created":"2023-12-14","cited_by_count":23},{"id":"1608.02367","title":"Learning Joint Representations of Videos and Sentences with Web Image Search","created":"2016-08-08","cited_by_count":17},{"id":"2311.07622","title":"Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval","created":"2023-11-13","cited_by_count":14},{"id":"2401.01823","title":"Detours for Navigating Instructional Videos","created":"2024-01-03","cited_by_count":7}],"next_cursor":null}