{"list":"other","total":62,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"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":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"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":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"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":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"id":"2012.00451","title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos","created":"2020-12-01","cited_by_count":248},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"id":"2202.10401","title":"Vision-Language Pre-Training with Triple Contrastive Learning","created":"2022-02-21","cited_by_count":212},{"id":"1808.02559","title":"A Joint Sequence Fusion Model for Video Question Answering and Retrieval","created":"2018-08-07","cited_by_count":208},{"id":"2111.12681","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","created":"2021-11-24","cited_by_count":188},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171},{"id":"2010.02824","title":"Support-set bottlenecks for video-text representation learning","created":"2020-10-06","cited_by_count":170},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149},{"id":"2203.15086","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","created":"2022-03-28","cited_by_count":128},{"id":"2104.10054","title":"T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval","created":"2021-04-20","cited_by_count":103},{"id":"2304.03307","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","created":"2023-04-06","cited_by_count":91},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87},{"id":"2201.04850","title":"Bridging Video-text Retrieval with Multiple Choice Questions","created":"2022-01-13","cited_by_count":79},{"id":"2003.07493","title":"Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection","created":"2020-03-17","cited_by_count":77},{"id":"2203.07111","title":"Disentangled Representation Learning for Text-Video Retrieval","created":"2022-03-14","cited_by_count":77},{"id":"2003.03186","title":"Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning","created":"2020-03-06","cited_by_count":74},{"id":"2209.06430","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","created":"2022-09-14","cited_by_count":74},{"id":"1610.02947","title":"End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering","created":"2016-10-10","cited_by_count":60},{"id":"2112.00656","title":"Object-aware Video-language Pre-training for Retrieval","created":"2021-12-01","cited_by_count":57},{"id":"2104.14085","title":"Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering","created":"2021-04-29","cited_by_count":56},{"id":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56},{"id":"2012.05710","title":"Look Before you Speak: Visually Contextualized Utterances","created":"2020-12-10","cited_by_count":53},{"id":"2107.12664","title":"Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection","created":"2021-07-27","cited_by_count":47},{"id":"2207.07885","title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","created":"2022-07-16","cited_by_count":41},{"id":"2204.12408","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","created":"2022-04-26","cited_by_count":29},{"id":"2205.05320","title":"Arbitrary Shape Text Detection via Boundary Transformer","created":"2022-05-11","cited_by_count":28},{"id":"2308.08414","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","created":"2023-08-16","cited_by_count":22},{"id":"2209.13307","title":"Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval","created":"2022-09-27","cited_by_count":20},{"id":"2304.03135","title":"VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision","created":"2023-04-06","cited_by_count":19},{"id":"2203.06410","title":"Kernel Proposal Network for Arbitrary Shape Text Detection","created":"2022-03-12","cited_by_count":17},{"id":"2208.12419","title":"Arbitrary Shape Text Detection via Segmentation with Probability Maps","created":"2022-08-26","cited_by_count":15},{"id":"2401.03637","title":"Inverse-like Antagonistic Scene Text Spotting via Reading-Order Estimation and Dynamic Sampling","created":"2024-01-08","cited_by_count":9},{"id":"2405.00352","title":"Transformer-based Reasoning for Learning Evolutionary Chain of Events on Temporal Knowledge Graph","created":"2024-05-01","cited_by_count":8},{"id":"2205.03562","title":"Graph Fusion Network for Multi-Oriented Object Detection","created":"2022-05-07","cited_by_count":7},{"id":"2308.03267","title":"Redundancy-aware Transformer for Video Question Answering","created":"2023-08-07","cited_by_count":7},{"id":"2209.15280","title":"Learning Transferable Spatiotemporal Representations from Natural Script Knowledge","created":"2022-09-30","cited_by_count":6}],"next_cursor":null}