{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"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":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"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":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"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":"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":"2307.06948","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","created":"2023-07-13","cited_by_count":272},{"id":"1712.00981","title":"Feature Generating Networks for Zero-Shot Learning","created":"2017-12-04","cited_by_count":257},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184},{"id":"2012.10071","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","created":"2020-12-18","cited_by_count":183},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"2103.16173","title":"Contrastive Embedding for Generalized Zero-Shot Learning","created":"2021-03-30","cited_by_count":94},{"id":"2304.03307","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","created":"2023-04-06","cited_by_count":91},{"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":"2108.02833","title":"Elaborative Rehearsal for Zero-shot Action Recognition","created":"2021-08-05","cited_by_count":77},{"id":"2012.10671","title":"SMART Frame Selection for Action Recognition","created":"2020-12-19","cited_by_count":73},{"id":"2101.07978","title":"Semantics Disentangling for Generalized Zero-Shot Learning","created":"2021-01-20","cited_by_count":56},{"id":"1904.08703","title":"Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition","created":"2019-04-18","cited_by_count":54},{"id":"1511.04458","title":"Transductive Zero-Shot Action Recognition by Word-Vector Embedding","created":"2015-11-13","cited_by_count":31},{"id":"1611.08663","title":"Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation","created":"2016-11-26","cited_by_count":27},{"id":"2107.00606","title":"Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition","created":"2021-07-01","cited_by_count":24},{"id":"2308.00313","title":"Zero-Shot Learning by Harnessing Adversarial Samples","created":"2023-08-01","cited_by_count":24},{"id":"2308.08414","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","created":"2023-08-16","cited_by_count":22},{"id":"2205.05313","title":"Towards Unified Prompt Tuning for Few-shot Text Classification","created":"2022-05-11","cited_by_count":18},{"id":"2107.13029","title":"A New Split for Evaluating True Zero-Shot Action Recognition","created":"2021-07-27","cited_by_count":14},{"id":"2304.02846","title":"Synthetic Sample Selection for Generalized Zero-Shot Learning","created":"2023-04-06","cited_by_count":14},{"id":"2312.08010","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","created":"2023-12-13","cited_by_count":14},{"id":"2101.07042","title":"CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition","created":"2021-01-18","cited_by_count":12},{"id":"2410.10497","title":"Continual Learning Improves Zero-Shot Action Recognition","created":"2024-10-14","cited_by_count":5},{"id":"2309.17327","title":"Telling Stories for Common Sense Zero-Shot Action Recognition","created":"2023-09-29","cited_by_count":4},{"id":"2408.02421","title":"FE-Adapter: Adapting Image-based Emotion Classifiers to Videos","created":"2024-08-05","cited_by_count":4}],"next_cursor":null}