{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"1711.10275","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","created":"2017-11-28","cited_by_count":748},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1904.09664","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","created":"2019-04-21","cited_by_count":648},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"1711.09869","title":"Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs","created":"2017-11-27","cited_by_count":385},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204},{"id":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175},{"id":"2203.14508","title":"Stratified Transformer for 3D Point Cloud Segmentation","created":"2022-03-28","cited_by_count":167},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153},{"id":"2103.01128","title":"InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring","created":"2021-03-01","cited_by_count":141},{"id":"2312.02010","title":"Towards Learning a Generalist Model for Embodied Navigation","created":"2023-12-04","cited_by_count":138},{"id":"2308.08769","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","created":"2023-08-17","cited_by_count":129},{"id":"2112.08879","title":"Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds","created":"2021-12-16","cited_by_count":128},{"id":"2105.11450","title":"SAT: 2D Semantics Assisted Training for 3D Visual Grounding","created":"2021-05-24","cited_by_count":124},{"id":"2211.09646","title":"Language Conditioned Spatial Relation Reasoning for 3D Object Grounding","created":"2022-11-17","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":"2211.15766","title":"Superpoint Transformer for 3D Scene Instance Segmentation","created":"2022-11-28","cited_by_count":116},{"id":"2204.06272","title":"3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection","created":"2022-04-13","cited_by_count":110},{"id":"2108.07478","title":"Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks","created":"2021-08-17","cited_by_count":99},{"id":"2209.14941","title":"EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding","created":"2022-09-29","cited_by_count":99},{"id":"1904.03282","title":"Weakly Supervised Video Moment Retrieval From Text Queries","created":"2019-04-05","cited_by_count":85},{"id":"2103.16381","title":"Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud","created":"2021-03-30","cited_by_count":81},{"id":"2208.02515","title":"Fine-Grained Semantically Aligned Vision-Language Pre-Training","created":"2022-08-04","cited_by_count":68},{"id":"2111.09571","title":"Person Re-identification Method Based on Color Attack and Joint Defence","created":"2021-11-18","cited_by_count":56},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49},{"id":"2002.08325","title":"VQA-LOL: Visual Question Answering under the Lens of Logic","created":"2020-02-19","cited_by_count":48},{"id":"2309.01692","title":"Mask-Attention-Free Transformer for 3D Instance Segmentation","created":"2023-09-04","cited_by_count":46},{"id":"2406.05127","title":"Towards Semantic Equivalence of Tokenization in Multimodal LLM","created":"2024-06-07","cited_by_count":45},{"id":"2308.16632","title":"3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation","created":"2023-08-31","cited_by_count":36},{"id":"2308.14575","title":"Referring Image Segmentation Using Text Supervision","created":"2023-08-28","cited_by_count":35},{"id":"2407.13761","title":"SegPoint: Segment Any Point Cloud via Large Language Model","created":"2024-07-18","cited_by_count":35},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32},{"id":"2405.17427","title":"Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model","created":"2024-05-27","cited_by_count":28},{"id":"2012.02356","title":"WeaQA: Weak Supervision via Captions for Visual Question Answering","created":"2020-12-04","cited_by_count":25},{"id":"2210.10775","title":"TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation","created":"2022-10-19","cited_by_count":25},{"id":"2108.02417","title":"Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval","created":"2021-08-05","cited_by_count":23},{"id":"2310.18049","title":"Text Augmented Spatial-aware Zero-shot Referring Image Segmentation","created":"2023-10-27","cited_by_count":21},{"id":"2402.15933","title":"Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA","created":"2024-02-24","cited_by_count":21},{"id":"2407.20664","title":"3D-GRES: Generalized 3D Referring Expression Segmentation","created":"2024-07-30","cited_by_count":18},{"id":"1712.08697","title":"Interpretable Counting for Visual Question Answering","created":"2017-12-23","cited_by_count":17},{"id":"2210.05668","title":"Understanding Embodied Reference with Touch-Line Transformer","created":"2022-10-11","cited_by_count":16},{"id":"2407.03263","title":"A Unified Framework for 3D Scene Understanding","created":"2024-07-03","cited_by_count":15},{"id":"2212.10278","title":"Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learning","created":"2022-12-17","cited_by_count":14},{"id":"2303.13186","title":"ScanERU: Interactive 3D Visual Grounding based on Embodied Reference Understanding","created":"2023-03-23","cited_by_count":12},{"id":"1912.03063","title":"Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks","created":"2019-12-06","cited_by_count":9},{"id":"2104.10412","title":"Comprehensive Multi-Modal Interactions for Referring Image Segmentation","created":"2021-04-21","cited_by_count":9},{"id":"2006.11747","title":"Weak Supervision and Referring Attention for Temporal-Textual Association Learning","created":"2020-06-21","cited_by_count":8},{"id":"2308.11887","title":"A Unified Framework for 3D Point Cloud Visual Grounding","created":"2023-08-23","cited_by_count":6},{"id":"2404.17273","title":"3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting","created":"2024-04-26","cited_by_count":6},{"id":"2302.09027","title":"CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension","created":"2023-02-17","cited_by_count":3}],"next_cursor":null}