{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"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":"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":"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":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"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":"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":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388},{"id":"2107.05720","title":"SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking","created":"2021-07-12","cited_by_count":286},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"2305.20088","title":"Improving CLIP Training with Language Rewrites","created":"2023-05-31","cited_by_count":217},{"id":"1907.13487","title":"Use What You Have: Video Retrieval Using Representations From Collaborative Experts","created":"2019-07-31","cited_by_count":214},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"2311.13165","title":"Multimodal Large Language Models: A Survey","created":"2023-11-22","cited_by_count":195},{"id":"2003.00392","title":"Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning","created":"2020-03-01","cited_by_count":180},{"id":"2010.02824","title":"Support-set bottlenecks for video-text representation learning","created":"2020-10-06","cited_by_count":170},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150},{"id":"2303.07678","title":"Query2doc: Query Expansion with Large Language Models","created":"2023-03-14","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":"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":"2207.07852","title":"TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval","created":"2022-07-16","cited_by_count":104},{"id":"2104.10054","title":"T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval","created":"2021-04-20","cited_by_count":103},{"id":"2301.00184","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","created":"2022-12-31","cited_by_count":90},{"id":"2205.00823","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","created":"2022-05-02","cited_by_count":86},{"id":"2104.08271","title":"TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval","created":"2021-04-16","cited_by_count":81},{"id":"2103.10699","title":"MDMMT: Multidomain Multimodal Transformer for Video Retrieval","created":"2021-03-19","cited_by_count":78},{"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":"2112.12777","title":"Cross Modal Retrieval with Querybank Normalisation","created":"2021-12-23","cited_by_count":72},{"id":"2102.12443","title":"A Straightforward Framework For Video Retrieval Using CLIP","created":"2021-02-24","cited_by_count":66},{"id":"2307.02869","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","created":"2023-07-06","cited_by_count":58},{"id":"2301.06309","title":"UATVR: Uncertainty-Adaptive Text-Video Retrieval","created":"2023-01-16","cited_by_count":55},{"id":"2309.10091","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","created":"2023-09-18","cited_by_count":49},{"id":"2009.07258","title":"BERT-QE: Contextualized Query Expansion for Document Re-ranking","created":"2020-09-15","cited_by_count":40},{"id":"2403.17998","title":"Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval","created":"2024-03-26","cited_by_count":33},{"id":"2109.05743","title":"Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation","created":"2021-09-13","cited_by_count":30},{"id":"1609.06782","title":"Deep Learning for Video Classification and Captioning","created":"2016-09-22","cited_by_count":28},{"id":"2001.05876","title":"Show, Recall, and Tell: Image Captioning with Recall Mechanism","created":"2020-01-15","cited_by_count":27},{"id":"2307.12964","title":"Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment","created":"2023-07-24","cited_by_count":21},{"id":"1506.01698","title":"The Long-Short Story of Movie Description","created":"2015-06-04","cited_by_count":20},{"id":"2209.13307","title":"Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval","created":"2022-09-27","cited_by_count":20},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16},{"id":"2309.09858","title":"Unsupervised Open-Vocabulary Object Localization in Videos","created":"2023-09-18","cited_by_count":13}],"next_cursor":null}