{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"2003.10580","title":"Meta Pseudo Labels","created":"2020-03-23","cited_by_count":374},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"2006.06882","title":"Rethinking Pre-training and Self-training","created":"2020-06-11","cited_by_count":352},{"id":"2101.06329","title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","created":"2021-01-15","cited_by_count":301},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"1905.00546","title":"Billion-scale semi-supervised learning for image classification","created":"2019-05-02","cited_by_count":232},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"2112.07910","title":"Decoupling Zero-Shot Semantic Segmentation","created":"2021-12-15","cited_by_count":199},{"id":"1804.07667","title":"Rethinking the Faster R-CNN Architecture for Temporal Action Localization","created":"2018-04-20","cited_by_count":194},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"id":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"2212.03588","title":"ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation","created":"2022-12-07","cited_by_count":178},{"id":"2207.05042","title":"Audio-Visual Segmentation","created":"2022-07-11","cited_by_count":151},{"id":"2007.10558","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing","created":"2020-07-21","cited_by_count":146},{"id":"2005.09629","title":"Improved Noisy Student Training for Automatic Speech Recognition","created":"2020-05-19","cited_by_count":141},{"id":"1909.09116","title":"Self-Training for End-to-End Speech Recognition","created":"2019-09-19","cited_by_count":129},{"id":"2007.06355","title":"Multiple Sound Sources Localization from Coarse to Fine","created":"2020-07-13","cited_by_count":118},{"id":"2010.05466","title":"Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching","created":"2020-10-12","cited_by_count":104},{"id":"2110.06615","title":"CLIP4Caption: CLIP for Video Caption","created":"2021-10-13","cited_by_count":88},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86},{"id":"2301.13190","title":"Audio-Visual Segmentation with Semantics","created":"2023-01-30","cited_by_count":75},{"id":"1902.07473","title":"Dual-modality seq2seq network for audio-visual event localization","created":"2019-02-20","cited_by_count":72},{"id":"2104.00239","title":"Positive Sample Propagation along the Audio-Visual Event Line","created":"2021-04-01","cited_by_count":69},{"id":"2103.16725","title":"SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification","created":"2021-03-30","cited_by_count":68},{"id":"2107.12960","title":"Enriching Local and Global Contexts for Temporal Action Localization","created":"2021-07-27","cited_by_count":64},{"id":"2211.09980","title":"Contrastive Positive Sample Propagation along the Audio-Visual Event Line","created":"2022-11-18","cited_by_count":50},{"id":"1904.09013","title":"Self-Supervised Audio-Visual Co-Segmentation","created":"2019-04-18","cited_by_count":44},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44},{"id":"2111.12374","title":"MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing","created":"2021-11-24","cited_by_count":39},{"id":"2210.15138","title":"Open-vocabulary Semantic Segmentation with Frozen Vision-Language Models","created":"2022-10-27","cited_by_count":39},{"id":"2206.03740","title":"Large Loss Matters in Weakly Supervised Multi-Label Classification","created":"2022-06-08","cited_by_count":38},{"id":"2203.16800","title":"Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization","created":"2022-03-31","cited_by_count":33},{"id":"1711.09550","title":"Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification","created":"2017-11-27","cited_by_count":29},{"id":"2204.11573","title":"Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing","created":"2022-04-25","cited_by_count":29},{"id":"2210.05060","title":"AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization","created":"2022-10-11","cited_by_count":28},{"id":"1711.01369","title":"Knowledge Transfer from Weakly Labeled Audio using Convolutional Neural Network for Sound Events and Scenes","created":"2017-11-04","cited_by_count":20},{"id":"1711.00927","title":"Audio Set classification with attention model: A probabilistic perspective","created":"2017-11-02","cited_by_count":14},{"id":"2209.00641","title":"Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition","created":"2022-08-31","cited_by_count":14},{"id":"2104.04598","title":"Cross-Modal learning for Audio-Visual Video Parsing","created":"2021-04-03","cited_by_count":4},{"id":"2203.16860","title":"Investigating Modality Bias in Audio Visual Video Parsing","created":"2022-03-31","cited_by_count":3}],"next_cursor":null}