{"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"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":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2309.15818","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","created":"2023-09-27","cited_by_count":302},{"id":"1705.08848","title":"Joint Distribution Optimal Transportation for Domain Adaptation","created":"2017-05-24","cited_by_count":282},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"1803.10081","title":"DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation","created":"2018-03-27","cited_by_count":214},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"1611.05088","title":"Learning a Deep Embedding Model for Zero-Shot Learning","created":"2016-11-15","cited_by_count":153},{"id":"2302.03024","title":"AIM: Adapting Image Models for Efficient Video Action Recognition","created":"2023-02-06","cited_by_count":148},{"id":"1803.05573","title":"Improving GANs Using Optimal Transport","created":"2018-03-15","cited_by_count":123},{"id":"2106.09141","title":"Probing Image-Language Transformers for Verb Understanding","created":"2021-06-16","cited_by_count":109},{"id":"2006.14744","title":"Graph Optimal Transport for Cross-Domain Alignment","created":"2020-06-26","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":"2108.02833","title":"Elaborative Rehearsal for Zero-shot Action Recognition","created":"2021-08-05","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":"2207.01297","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","created":"2022-07-04","cited_by_count":71},{"id":"1906.02085","title":"GOT: An Optimal Transport framework for Graph comparison","created":"2019-06-05","cited_by_count":64},{"id":"2210.01253","title":"PLOT: Prompt Learning with Optimal Transport for Vision-Language Models","created":"2022-10-03","cited_by_count":64},{"id":"2210.01115","title":"LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models","created":"2022-10-03","cited_by_count":59},{"id":"2306.05493","title":"Multi-Modal Classifiers for Open-Vocabulary Object Detection","created":"2023-06-08","cited_by_count":53},{"id":"1703.10664","title":"Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos","created":"2017-03-30","cited_by_count":50},{"id":"2304.10465","title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","created":"2023-04-20","cited_by_count":46},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43},{"id":"2309.07911","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","created":"2023-09-14","cited_by_count":32},{"id":"2301.12171","title":"ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Prompts","created":"2023-01-28","cited_by_count":16},{"id":"2105.07085","title":"MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations","created":"2021-05-14","cited_by_count":13},{"id":"1705.01781","title":"Am I Done? Predicting Action Progress in Videos","created":"2017-05-04","cited_by_count":11},{"id":"2306.13380","title":"First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment","created":"2023-06-23","cited_by_count":3},{"id":"2308.11249","title":"Video BagNet: short temporal receptive fields increase robustness in long-term action recognition","created":"2023-08-22","cited_by_count":2}],"next_cursor":null}