{"list":"other","total":74,"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"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":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"id":"1711.02281","title":"Non-Autoregressive Neural Machine Translation","created":"2017-11-07","cited_by_count":463},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"2104.14806","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","created":"2021-04-30","cited_by_count":256},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"2402.08268","title":"World Model on Million-Length Video And Language With Blockwise RingAttention","created":"2024-02-13","cited_by_count":198},{"id":"2302.01329","title":"Dreamix: Video Diffusion Models are General Video Editors","created":"2023-02-02","cited_by_count":191},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154},{"id":"2305.04160","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","created":"2023-05-07","cited_by_count":128},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126},{"id":"2109.04290","title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","created":"2021-09-09","cited_by_count":116},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105},{"id":"2402.03161","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","created":"2024-02-05","cited_by_count":100},{"id":"2304.14404","title":"Motion-Conditioned Diffusion Model for Controllable Video Synthesis","created":"2023-04-27","cited_by_count":99},{"id":"2005.00214","title":"The AVA-Kinetics Localized Human Actions Video Dataset","created":"2020-05-01","cited_by_count":82},{"id":"2312.09158","title":"General Object Foundation Model for Images and Videos at Scale","created":"2023-12-14","cited_by_count":71},{"id":"2304.14407","title":"ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System","created":"2023-04-27","cited_by_count":65},{"id":"2106.11250","title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning","created":"2021-06-21","cited_by_count":56},{"id":"2311.13435","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","created":"2023-11-22","cited_by_count":51},{"id":"2305.13840","title":"Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback Learning","created":"2023-05-23","cited_by_count":48},{"id":"2402.05861","title":"Memory Consolidation Enables Long-Context Video Understanding","created":"2024-02-08","cited_by_count":45},{"id":"2403.13248","title":"Mora: Enabling Generalist Video Generation via A Multi-Agent Framework","created":"2024-03-20","cited_by_count":45},{"id":"1609.08124","title":"Learning Language-Visual Embedding for Movie Understanding with Natural-Language","created":"2016-09-26","cited_by_count":41},{"id":"2312.11782","title":"Learning Object State Changes in Videos: An Open-World Perspective","created":"2023-12-19","cited_by_count":36},{"id":"2307.07063","title":"Bootstrapping Vision-Language Learning with Decoupled Language Pre-training","created":"2023-07-13","cited_by_count":28},{"id":"2312.00968","title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","created":"2023-12-01","cited_by_count":26},{"id":"2207.07646","title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","created":"2022-07-15","cited_by_count":22},{"id":"2310.05863","title":"Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models","created":"2023-10-09","cited_by_count":21},{"id":"2309.16669","title":"Training a Large Video Model on a Single Machine in a Day","created":"2023-09-28","cited_by_count":20},{"id":"2401.06129","title":"Distilling Vision-Language Models on Millions of Videos","created":"2024-01-11","cited_by_count":20},{"id":"2307.03166","title":"VideoGLUE: Video General Understanding Evaluation of Foundation Models","created":"2023-07-06","cited_by_count":14},{"id":"2312.08010","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","created":"2023-12-13","cited_by_count":14},{"id":"2204.07892","title":"Video Action Detection: Analysing Limitations and Challenges","created":"2022-04-17","cited_by_count":12},{"id":"2401.11649","title":"M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition","created":"2024-01-22","cited_by_count":11},{"id":"2402.10698","title":"Question-Instructed Visual Descriptions for Zero-Shot Video Question Answering","created":"2024-02-16","cited_by_count":9},{"id":"2402.10896","title":"PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter","created":"2024-02-16","cited_by_count":7},{"id":"2306.06010","title":"A Large-Scale Analysis on Self-Supervised Video Representation Learning","created":"2023-06-09","cited_by_count":5},{"id":"2310.15324","title":"Videoprompter: an ensemble of foundational models for zero-shot video understanding","created":"2023-10-23","cited_by_count":5},{"id":"2402.00868","title":"We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baseline","created":"2024-02-01","cited_by_count":4},{"id":"2307.09972","title":"Fine-grained Text-Video Retrieval with Frozen Image Encoders","created":"2023-07-14","cited_by_count":2}],"next_cursor":null}