{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"2302.10663","title":"RealFusion: 360{\\deg} Reconstruction of Any Object from a Single Image","created":"2023-02-21","cited_by_count":306},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"1708.07632","title":"Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition","created":"2017-08-25","cited_by_count":178},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"1405.2941","title":"Cross-view Action Modeling, Learning and Recognition","created":"2014-05-12","cited_by_count":134},{"id":"1905.05908","title":"Task-Driven Modular Networks for Zero-Shot Compositional Learning","created":"2019-05-15","cited_by_count":121},{"id":"1912.09930","title":"Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks","created":"2019-12-20","cited_by_count":114},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"2101.12609","title":"Open World Compositional Zero-Shot Learning","created":"2021-01-29","cited_by_count":101},{"id":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96},{"id":"2004.00587","title":"Symmetry and Group in Attribute-Object Compositions","created":"2020-04-01","cited_by_count":89},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65},{"id":"1905.05143","title":"VideoGraph: Recognizing Minutes-Long Human Activities in Videos","created":"2019-05-13","cited_by_count":57},{"id":"2205.08536","title":"Disentangling Visual Embeddings for Attributes and Objects","created":"2022-05-17","cited_by_count":55},{"id":"2105.01017","title":"Learning Graph Embeddings for Open World Compositional Zero-Shot Learning","created":"2021-05-03","cited_by_count":49},{"id":"1805.02834","title":"Weakly-Supervised Video Object Grounding from Text by Loss Weighting and Object Interaction","created":"2018-05-08","cited_by_count":40},{"id":"2203.15187","title":"ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization","created":"2022-03-29","cited_by_count":40},{"id":"2203.11637","title":"Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos","created":"2022-03-22","cited_by_count":39},{"id":"1808.07784","title":"Time-Agnostic Prediction: Predicting Predictable Video Frames","created":"2018-08-23","cited_by_count":37},{"id":"2303.14124","title":"Towards Scalable Neural Representation for Diverse Videos","created":"2023-03-24","cited_by_count":37},{"id":"2004.04968","title":"Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?","created":"2020-04-10","cited_by_count":31},{"id":"1702.02738","title":"Joint Discovery of Object States and Manipulation Actions","created":"2017-02-09","cited_by_count":28},{"id":"2012.08510","title":"GTA: Global Temporal Attention for Video Action Understanding","created":"2020-12-15","cited_by_count":20},{"id":"2108.04603","title":"Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition","created":"2021-08-10","cited_by_count":19},{"id":"2111.01936","title":"Revisiting spatio-temporal layouts for compositional action recognition","created":"2021-11-02","cited_by_count":19},{"id":"2101.02337","title":"Learning Temporal Dynamics from Cycles in Narrated Video","created":"2021-01-07","cited_by_count":13},{"id":"1906.04854","title":"Task-Aware Feature Generation for Zero-Shot Compositional Learning","created":"2019-06-11","cited_by_count":11},{"id":"2211.13500","title":"Multi-Task Learning of Object State Changes from Uncurated Videos","created":"2022-11-24","cited_by_count":10},{"id":"2104.07098","title":"StEP: Style-based Encoder Pre-training for Multi-modal Image Synthesis","created":"2021-04-14","cited_by_count":7},{"id":"2201.04906","title":"Hand-Object Interaction Reasoning","created":"2022-01-13","cited_by_count":7},{"id":"1906.05147","title":"Recognizing Manipulation Actions from State-Transformations","created":"2019-06-12","cited_by_count":6},{"id":"2012.02109","title":"SAFCAR: Structured Attention Fusion for Compositional Action Recognition","created":"2020-12-03","cited_by_count":4}],"next_cursor":null}