{"list":"other","total":52,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"id":"1906.00817","title":"Zero-Shot Semantic Segmentation","created":"2019-06-03","cited_by_count":245},{"id":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231},{"id":"2303.11797","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","created":"2023-03-21","cited_by_count":219},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"2112.07910","title":"Decoupling Zero-Shot Semantic Segmentation","created":"2021-12-15","cited_by_count":199},{"id":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151},{"id":"2007.09183","title":"Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation","created":"2020-07-17","cited_by_count":122},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117},{"id":"2109.03814","title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","created":"2021-09-08","cited_by_count":109},{"id":"1905.10089","title":"ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation","created":"2019-05-24","cited_by_count":107},{"id":"1903.01177","title":"PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things","created":"2019-03-04","cited_by_count":98},{"id":"2311.15537","title":"SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation","created":"2023-11-27","cited_by_count":97},{"id":"2311.14405","title":"OneFormer3D: One Transformer for Unified Point Cloud Segmentation","created":"2023-11-24","cited_by_count":95},{"id":"2011.06961","title":"Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis","created":"2020-11-13","cited_by_count":84},{"id":"2108.10528","title":"ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation","created":"2021-08-24","cited_by_count":77},{"id":"1803.06791","title":"Depth-aware CNN for RGB-D Segmentation","created":"2018-03-19","cited_by_count":74},{"id":"1808.03833","title":"Self-Supervised Model Adaptation for Multimodal Semantic Segmentation","created":"2018-08-11","cited_by_count":73},{"id":"1806.01054","title":"RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation","created":"2018-06-04","cited_by_count":66},{"id":"2309.09668","title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","created":"2023-09-18","cited_by_count":60},{"id":"2310.00240","title":"Learning Mask-aware CLIP Representations for Zero-Shot Segmentation","created":"2023-09-30","cited_by_count":57},{"id":"2312.04089","title":"Open-Vocabulary Segmentation with Semantic-Assisted Calibration","created":"2023-12-07","cited_by_count":49},{"id":"2301.09506","title":"OvarNet: Towards Open-vocabulary Object Attribute Recognition","created":"2023-01-23","cited_by_count":43},{"id":"2109.10165","title":"Panoptic Multi-TSDFs: a Flexible Representation for Online Multi-resolution Volumetric Mapping and Long-term Dynamic Scene Consistency","created":"2021-09-21","cited_by_count":39},{"id":"2303.11324","title":"Open-vocabulary Panoptic Segmentation with Embedding Modulation","created":"2023-03-20","cited_by_count":39},{"id":"1909.04631","title":"Bayesian Spatial Kernel Smoothing for Scalable Dense Semantic Mapping","created":"2019-09-10","cited_by_count":35},{"id":"2207.04526","title":"Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments","created":"2022-07-10","cited_by_count":33},{"id":"2007.09365","title":"Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing","created":"2020-07-18","cited_by_count":24},{"id":"2401.06704","title":"Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering","created":"2024-01-12","cited_by_count":14},{"id":"2304.06957","title":"MVP-SEG: Multi-View Prompt Learning for Open-Vocabulary Semantic Segmentation","created":"2023-04-14","cited_by_count":10},{"id":"2306.05242","title":"Efficient Multi-Task Scene Analysis with RGB-D Transformers","created":"2023-06-08","cited_by_count":7},{"id":"2309.13635","title":"PanopticNDT: Efficient and Robust Panoptic Mapping","created":"2023-09-24","cited_by_count":6},{"id":"2203.05836","title":"Efficient and Robust Semantic Mapping for Indoor Environments","created":"2022-03-11","cited_by_count":5}],"next_cursor":null}