Sheng Jin

EduGuardBench: A Holistic Benchmark for Evaluating the Pedagogical Fidelity and Adversarial Safety of LLMs as Simulated Teachers AAAI 2026 AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks AAAI 2025 EMNLP: Educator-role Moral and Normative Large Language Models Profiling EMNLP 2025 Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamics EMNLP 2025 F-LMM: Grounding Frozen Large Multimodal Models CVPR 2025 Frame-Voyager: Learning to Query Frames for Video Large Language Models ICLR 2025 Harmonizing Visual Representations for Unified Multimodal Understanding and Generation ICCV 2025 NADER: Neural Architecture Design via Multi-Agent Collaboration CVPR 2025 Ultra-High Resolution Segmentation via Boundary-Enhanced Patch-Merging Transformer AAAI 2025 Unsupervised Continual Domain Shift Learning with Multi-Prototype Modeling CVPR 2025 CLIM: Contrastive Language-Image Mosaic for Region Representation AAAI 2024 CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction ICLR 2024 GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition ECCV 2024 KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension NeurIPS 2024 LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors ICLR 2024 MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders NeurIPS 2024 PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation ICLR 2024 Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution NeurIPS 2024 UniFS: Universal Few-shot Instance Perception with Point Representations ECCV 2024 Weakly Supervised Monocular 3D Detection with a Single-View Image CVPR 2024 When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset ECCV 2024 You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception ECCV 2024 Aligning Bag of Regions for Open-Vocabulary Object Detection CVPR 2023 Category-Extensible Out-of-Distribution Detection via Hierarchical Context Descriptions NeurIPS 2023 Domain Generalization via Balancing Training Difficulty and Model Capability ICCV 2023 Uncertainty-aware Unsupervised Multi-Object Tracking ICCV 2023 3D Interacting Hand Pose Estimation by Hand De-Occlusion and Removal ECCV 2022 Not All Tokens Are Equal: Human-Centric Visual Analysis via Token Clustering Transformer CVPR 2022 Pose for Everything: Towards Category-Agnostic Pose Estimation ECCV 2022 PoseTrans: A Simple yet Effective Pose Transformation Augmentation for Human Pose Estimation ECCV 2022 Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization ICLR 2022 Temporal Action Proposal Generation with Background Constraint AAAI 2022 Asynchronous Teacher Guided Bit-wise Hard Mining for Online Hashing AAAI 2021 Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images ICCV 2021 ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search CVPR 2021 When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks CVPR 2021 Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation ECCV 2020 HoMM: Higher-Order Moment Matching for Unsupervised Domain Adaptation AAAI 2020 RL-Duet: Online Music Accompaniment Generation Using Deep Reinforcement Learning AAAI 2020 SSAH: Semi-Supervised Adversarial Deep Hashing with Self-Paced Hard Sample Generation AAAI 2020 When Counterpoint Meets Chinese Folk Melodies NeurIPS 2020 Whole-Body Human Pose Estimation in the Wild ECCV 2020 Multi-Person Articulated Tracking With Spatial and Temporal Embeddings CVPR 2019 TRB: A Novel Triplet Representation for Understanding 2D Human Body ICCV 2019 Connectionist Temporal Classification with Maximum Entropy Regularization NeurIPS 2018