{"list":"other","total":69,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"1808.04560","title":"Deep Retinex Decomposition for Low-Light Enhancement","created":"2018-08-14","cited_by_count":723},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"1505.04366","title":"Learning Deconvolution Network for Semantic Segmentation","created":"2015-05-17","cited_by_count":365},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"1906.07165","title":"High Speed and High Dynamic Range Video with an Event Camera","created":"2019-06-15","cited_by_count":345},{"id":"1812.08156","title":"Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion","created":"2018-12-19","cited_by_count":307},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"id":"1801.10202","title":"The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception","created":"2018-01-30","cited_by_count":254},{"id":"1802.06898","title":"EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras","created":"2018-02-19","cited_by_count":224},{"id":"1803.07913","title":"HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification","created":"2018-03-21","cited_by_count":218},{"id":"1911.06667","title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","created":"2019-11-15","cited_by_count":201},{"id":"1507.00448","title":"Cross Modal Distillation for Supervision Transfer","created":"2015-07-02","cited_by_count":175},{"id":"1901.03784","title":"UPSNet: A Unified Panoptic Segmentation Network","created":"2019-01-12","cited_by_count":175},{"id":"2304.04155","title":"Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imaging","created":"2023-04-09","cited_by_count":161},{"id":"2212.05598","title":"Recurrent Vision Transformers for Object Detection with Event Cameras","created":"2022-12-11","cited_by_count":159},{"id":"2106.07286","title":"TimeLens: Event-based Video Frame Interpolation","created":"2021-06-14","cited_by_count":151},{"id":"2106.03164","title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","created":"2021-06-06","cited_by_count":147},{"id":"2307.11795","title":"Prompting Large Language Models with Speech Recognition Abilities","created":"2023-07-21","cited_by_count":140},{"id":"2108.05015","title":"VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows","created":"2021-08-11","cited_by_count":129},{"id":"1803.04523","title":"Event-based Moving Object Detection and Tracking","created":"2018-03-12","cited_by_count":127},{"id":"1910.07655","title":"Deep Semantic Segmentation of Natural and Medical Images: A Review","created":"2019-10-16","cited_by_count":125},{"id":"1704.06857","title":"A Review on Deep Learning Techniques Applied to Semantic Segmentation","created":"2017-04-22","cited_by_count":122},{"id":"2203.17149","title":"AEGNN: Asynchronous Event-based Graph Neural Networks","created":"2022-03-31","cited_by_count":118},{"id":"2203.17191","title":"Time Lens++: Event-based Frame Interpolation with Parametric Non-linear Flow and Multi-scale Fusion","created":"2022-03-31","cited_by_count":111},{"id":"1811.12039","title":"EV-SegNet: Semantic Segmentation for Event-based Cameras","created":"2018-11-29","cited_by_count":93},{"id":"2207.10022","title":"Secrets of Event-Based Optical Flow","created":"2022-07-20","cited_by_count":92},{"id":"2109.09052","title":"Object Tracking by Jointly Exploiting Frame and Event Domain","created":"2021-09-19","cited_by_count":84},{"id":"1806.07110","title":"Modality Distillation with Multiple Stream Networks for Action Recognition","created":"2018-06-19","cited_by_count":83},{"id":"1904.07235","title":"Focus Is All You Need: Loss Functions For Event-based Vision","created":"2019-04-15","cited_by_count":83},{"id":"2203.10016","title":"ESS: Learning Event-based Semantic Segmentation from Still Images","created":"2022-03-18","cited_by_count":82},{"id":"1904.01293","title":"Event-Based Motion Segmentation by Motion Compensation","created":"2019-04-02","cited_by_count":78},{"id":"2211.09078","title":"Learning Dense and Continuous Optical Flow from an Event Camera","created":"2022-11-16","cited_by_count":60},{"id":"2211.11010","title":"Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metric","created":"2022-11-20","cited_by_count":52},{"id":"2012.08730","title":"Event-based Motion Segmentation with Spatio-Temporal Graph Cuts","created":"2020-12-16","cited_by_count":50},{"id":"2111.12341","title":"EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation","created":"2021-11-24","cited_by_count":47},{"id":"1910.04641","title":"Cross-modal knowledge distillation for action recognition","created":"2019-10-10","cited_by_count":45},{"id":"2307.04129","title":"Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers","created":"2023-07-09","cited_by_count":43},{"id":"2308.10837","title":"Leveraging Large Language Models for Pre-trained Recommender Systems","created":"2023-08-21","cited_by_count":42},{"id":"2310.01647","title":"Equivariant Adaptation of Large Pretrained Models","created":"2023-10-02","cited_by_count":41},{"id":"2306.02245","title":"SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model","created":"2023-06-04","cited_by_count":40},{"id":"2203.06622","title":"Multi-Bracket High Dynamic Range Imaging with Event Cameras","created":"2022-03-13","cited_by_count":37},{"id":"2109.01801","title":"Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation","created":"2021-09-04","cited_by_count":32},{"id":"2304.06600","title":"Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation","created":"2023-04-13","cited_by_count":29},{"id":"2301.05191","title":"A Unified Framework for Event-based Frame Interpolation with Ad-hoc Deblurring in the Wild","created":"2023-01-12","cited_by_count":27},{"id":"2004.00280","title":"Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal Hashing","created":"2020-04-01","cited_by_count":26},{"id":"2309.15082","title":"RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation","created":"2023-09-26","cited_by_count":26},{"id":"1909.11874","title":"Compact Trilinear Interaction for Visual Question Answering","created":"2019-09-26","cited_by_count":24},{"id":"1911.08730","title":"Event-based Object Detection and Tracking for Space Situational Awareness","created":"2019-11-20","cited_by_count":19},{"id":"2311.01403","title":"REAL: Resilience and Adaptation using Large Language Models on Autonomous Aerial Robots","created":"2023-11-02","cited_by_count":19},{"id":"1911.04553","title":"Towards Low-Latency High-Bandwidth Control of Quadrotors using Event Cameras","created":"2019-11-11","cited_by_count":14},{"id":"1807.07682","title":"Cross-Modality Distillation: A case for Conditional Generative Adversarial Networks","created":"2018-07-20","cited_by_count":11}],"next_cursor":null}