{"list":"other","total":58,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"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":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"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":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474},{"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":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2409.04429","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","created":"2024-09-06","cited_by_count":295},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169},{"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":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117},{"id":"2305.10400","title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","created":"2023-05-17","cited_by_count":108},{"id":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105},{"id":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87},{"id":"1809.01337","title":"Localizing Moments in Video with Temporal Language","created":"2018-09-05","cited_by_count":83},{"id":"2304.14530","title":"Generating images of rare concepts using pre-trained diffusion models","created":"2023-04-27","cited_by_count":79},{"id":"2303.12112","title":"Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation","created":"2023-03-21","cited_by_count":78},{"id":"2309.13415","title":"Dream the Impossible: Outlier Imagination with Diffusion Models","created":"2023-09-23","cited_by_count":77},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76},{"id":"1907.08340","title":"Only Time Can Tell: Discovering Temporal Data for Temporal Modeling","created":"2019-07-19","cited_by_count":67},{"id":"2411.02545","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives","created":"2024-11-04","cited_by_count":58},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51},{"id":"2401.07781","title":"Towards A Better Metric for Text-to-Video Generation","created":"2024-01-15","cited_by_count":51},{"id":"2305.15316","title":"Training on Thin Air: Improve Image Classification with Generated Data","created":"2023-05-24","cited_by_count":50},{"id":"2306.01879","title":"Revisiting the Role of Language Priors in Vision-Language Models","created":"2023-06-02","cited_by_count":50},{"id":"2312.00081","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","created":"2023-11-30","cited_by_count":46},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42},{"id":"2111.08919","title":"EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching","created":"2021-11-17","cited_by_count":36},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32},{"id":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30},{"id":"2310.02835","title":"Delving into CLIP latent space for Video Anomaly Recognition","created":"2023-10-04","cited_by_count":27},{"id":"2312.01564","title":"APoLLo: Unified Adapter and Prompt Learning for Vision Language Models","created":"2023-12-04","cited_by_count":19},{"id":"2209.11388","title":"LGDN: Language-Guided Denoising Network for Video-Language Modeling","created":"2022-09-23","cited_by_count":11}],"next_cursor":null}