{"list":"other","total":55,"rows":[{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"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":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"1908.02983","title":"Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning","created":"2019-08-08","cited_by_count":510},{"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":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"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":"2203.14940","title":"Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model","created":"2022-03-28","cited_by_count":317},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162},{"id":"1611.05088","title":"Learning a Deep Embedding Model for Zero-Shot Learning","created":"2016-11-15","cited_by_count":153},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"2102.04130","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","created":"2021-02-08","cited_by_count":141},{"id":"2003.13942","title":"Spatio-Temporal Graph for Video Captioning with Knowledge Distillation","created":"2020-03-31","cited_by_count":109},{"id":"2110.06615","title":"CLIP4Caption: CLIP for Video Caption","created":"2021-10-13","cited_by_count":88},{"id":"2003.01455","title":"Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications","created":"2020-03-03","cited_by_count":80},{"id":"1811.10787","title":"Unsupervised Image Captioning","created":"2018-11-27","cited_by_count":79},{"id":"2201.04850","title":"Bridging Video-text Retrieval with Multiple Choice Questions","created":"2022-01-13","cited_by_count":79},{"id":"2108.02833","title":"Elaborative Rehearsal for Zero-shot Action Recognition","created":"2021-08-05","cited_by_count":77},{"id":"1908.09317","title":"Towards Unsupervised Image Captioning with Shared Multimodal Embeddings","created":"2019-08-25","cited_by_count":54},{"id":"1803.08460","title":"Towards Universal Representation for Unseen Action Recognition","created":"2018-03-22","cited_by_count":44},{"id":"1909.02201","title":"Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach","created":"2019-09-05","cited_by_count":30},{"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":"1705.00930","title":"Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner","created":"2017-05-02","cited_by_count":21},{"id":"1909.03396","title":"Quality Estimation for Image Captions Based on Large-scale Human Evaluations","created":"2019-09-08","cited_by_count":17},{"id":"2008.12432","title":"All About Knowledge Graphs for Actions","created":"2020-08-28","cited_by_count":16},{"id":"2203.13371","title":"FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks","created":"2022-03-24","cited_by_count":16},{"id":"2205.01657","title":"Cross-modal Representation Learning for Zero-shot Action Recognition","created":"2022-05-03","cited_by_count":15},{"id":"2203.15381","title":"Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification","created":"2022-03-29","cited_by_count":11},{"id":"2110.13479","title":"Zero-Shot Action Recognition from Diverse Object-Scene Compositions","created":"2021-10-26","cited_by_count":8},{"id":"2207.01708","title":"Disentangled Action Recognition with Knowledge Bases","created":"2022-07-04","cited_by_count":6},{"id":"2110.05204","title":"CLIP4Caption ++: Multi-CLIP for Video Caption","created":"2021-10-11","cited_by_count":5},{"id":"2201.04023","title":"Boosting Video Representation Learning with Multi-Faceted Integration","created":"2022-01-11","cited_by_count":5},{"id":"2203.03971","title":"Universal Prototype Transport for Zero-Shot Action Recognition and Localization","created":"2022-03-08","cited_by_count":4},{"id":"2209.12061","title":"Global Semantic Descriptors for Zero-Shot Action Recognition","created":"2022-09-24","cited_by_count":2}],"next_cursor":null}