{"list":"other","total":79,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"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":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"1803.10464","title":"Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation","created":"2018-03-28","cited_by_count":321},{"id":"2004.04581","title":"Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation","created":"2020-04-09","cited_by_count":300},{"id":"1906.00817","title":"Zero-Shot Semantic Segmentation","created":"2019-06-03","cited_by_count":245},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"2112.07910","title":"Decoupling Zero-Shot Semantic Segmentation","created":"2021-12-15","cited_by_count":199},{"id":"1603.06098","title":"Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation","created":"2016-03-19","cited_by_count":198},{"id":"2008.03898","title":"Prototype Mixture Models for Few-shot Semantic Segmentation","created":"2020-08-10","cited_by_count":190},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2007.06309","title":"Part-aware Prototype Network for Few-shot Semantic Segmentation","created":"2020-07-13","cited_by_count":162},{"id":"2007.01947","title":"Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation","created":"2020-07-03","cited_by_count":144},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"2203.02891","title":"Multi-class Token Transformer for Weakly Supervised Semantic Segmentation","created":"2022-03-06","cited_by_count":138},{"id":"2103.08896","title":"Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation","created":"2021-03-16","cited_by_count":134},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"1804.09626","title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","created":"2018-04-25","cited_by_count":128},{"id":"2105.08965","title":"Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation","created":"2021-05-19","cited_by_count":127},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"2203.02664","title":"Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers","created":"2022-03-05","cited_by_count":118},{"id":"2212.09506","title":"CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation","created":"2022-12-16","cited_by_count":118},{"id":"2310.01403","title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","created":"2023-10-02","cited_by_count":118},{"id":"2108.03032","title":"Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer","created":"2021-08-06","cited_by_count":116},{"id":"2103.14581","title":"Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation","created":"2021-03-26","cited_by_count":95},{"id":"2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","created":"2023-09-21","cited_by_count":90},{"id":"1911.08039","title":"Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach","created":"2019-11-19","cited_by_count":88},{"id":"2104.07256","title":"A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation","created":"2021-04-15","cited_by_count":79},{"id":"1509.03150","title":"STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation","created":"2015-09-10","cited_by_count":78},{"id":"2208.03826","title":"Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications","created":"2022-08-07","cited_by_count":78},{"id":"2108.03852","title":"Complementary Patch for Weakly Supervised Semantic Segmentation","created":"2021-08-09","cited_by_count":75},{"id":"2203.02668","title":"Cross Language Image Matching for Weakly Supervised Semantic Segmentation","created":"2022-03-05","cited_by_count":72},{"id":"2103.01795","title":"Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation","created":"2021-03-02","cited_by_count":69},{"id":"2211.13222","title":"SVFormer: Semi-supervised Video Transformer for Action Recognition","created":"2022-11-23","cited_by_count":68},{"id":"2303.01267","title":"Token Contrast for Weakly-Supervised Semantic Segmentation","created":"2023-03-02","cited_by_count":65},{"id":"1811.10698","title":"LSTA: Long Short-Term Attention for Egocentric Action Recognition","created":"2018-11-26","cited_by_count":57},{"id":"2108.12995","title":"Pseudo-mask Matters in Weakly-supervised Semantic Segmentation","created":"2021-08-30","cited_by_count":48},{"id":"2303.13471","title":"Egocentric Audio-Visual Object Localization","created":"2023-03-23","cited_by_count":40},{"id":"2309.08816","title":"EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding","created":"2023-09-15","cited_by_count":40},{"id":"2002.08098","title":"Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning","created":"2020-02-19","cited_by_count":37},{"id":"2203.16045","title":"Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds","created":"2022-03-30","cited_by_count":37},{"id":"2308.14575","title":"Referring Image Segmentation Using Text Supervision","created":"2023-08-28","cited_by_count":35},{"id":"2201.05729","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","created":"2022-01-15","cited_by_count":32},{"id":"2301.01380","title":"Ego-Only: Egocentric Action Detection without Exocentric Transferring","created":"2023-01-03","cited_by_count":31},{"id":"2307.07483","title":"Multimodal Distillation for Egocentric Action Recognition","created":"2023-07-14","cited_by_count":28},{"id":"2301.10931","title":"Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning","created":"2023-01-26","cited_by_count":26},{"id":"2305.07214","title":"MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition","created":"2023-05-12","cited_by_count":26},{"id":"2308.11488","title":"Opening the Vocabulary of Egocentric Actions","created":"2023-08-22","cited_by_count":23},{"id":"2011.10972","title":"Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning","created":"2020-11-22","cited_by_count":22},{"id":"2108.01344","title":"Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation","created":"2021-08-03","cited_by_count":22},{"id":"2308.03005","title":"MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation","created":"2023-08-06","cited_by_count":22},{"id":"2308.12035","title":"RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D","created":"2023-08-23","cited_by_count":21},{"id":"2311.17041","title":"Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties","created":"2023-11-28","cited_by_count":21},{"id":"2012.09503","title":"Embodied Visual Active Learning for Semantic Segmentation","created":"2020-12-17","cited_by_count":19},{"id":"2202.04812","title":"Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling","created":"2022-02-10","cited_by_count":19},{"id":"2203.11305","title":"Generative Adversarial Network for Future Hand Segmentation from Egocentric Video","created":"2022-03-21","cited_by_count":16},{"id":"2309.02423","title":"EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding","created":"2023-09-05","cited_by_count":15},{"id":"2108.07413","title":"Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation","created":"2021-08-17","cited_by_count":13},{"id":"2304.09913","title":"MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation","created":"2023-04-19","cited_by_count":13},{"id":"2311.17450","title":"Continual Learning for Image Segmentation with Dynamic Query","created":"2023-11-29","cited_by_count":12},{"id":"2212.05286","title":"A Survey of Multi-Agent Human-Robot Interaction Systems","created":"2022-12-10","cited_by_count":10},{"id":"2403.05856","title":"POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-View World","created":"2024-03-09","cited_by_count":10},{"id":"2011.07252","title":"Ego2Hands: A Dataset for Egocentric Two-hand Segmentation and Detection","created":"2020-11-14","cited_by_count":9},{"id":"2310.15066","title":"Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge","created":"2023-10-23","cited_by_count":8},{"id":"2003.12352","title":"Enhanced Self-Perception in Mixed Reality: Egocentric Arm Segmentation and Database with Automatic Labelling","created":"2020-03-27","cited_by_count":6},{"id":"2307.03918","title":"VS-TransGRU: A Novel Transformer-GRU-based Framework Enhanced by Visual-Semantic Fusion for Egocentric Action Anticipation","created":"2023-07-08","cited_by_count":4},{"id":"2207.01296","title":"Real Time Egocentric Segmentation for Video-self Avatar in Mixed Reality","created":"2022-07-04","cited_by_count":2},{"id":"2210.11387","title":"Transformer-based Action recognition in hand-object interacting scenarios","created":"2022-10-20","cited_by_count":2}],"next_cursor":null}