Shiliang Pu

Fast Updating Truncated SVD for Representation Learning with Sparse Matrices ICLR 2024 Learning to solve Class-Constrained Bin Packing Problems via Encoder-Decoder Model ICLR 2024 LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin ACL 2024 Insert or Attach: Taxonomy Completion via Box Embedding ACL 2024 Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning AAAI 2024 MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognition EMNLP 2023 Multi-View Adversarial Discriminator: Mine the Non-Causal Factors for Object Detection in Unseen Domains CVPR 2023 Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization CVPR 2023 Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation CVPR 2023 PHA: Patch-Wise High-Frequency Augmentation for Transformer-Based Person Re-Identification CVPR 2023 Select and Optimize: Learning to solve large-scale TSP instances AISTATS 2023 Towards Deployment-Efficient and Collision-Free Multi-Agent Path Finding (Student Abstract) AAAI 2023 Multi-modal Action Chain Abductive Reasoning ACL 2023 Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object Detection ICCV 2023 Clusterformer: Cluster-based Transformer for 3D Object Detection in Point Clouds ICCV 2023 Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation ICCV 2023 Mixed-Dual-Head Meets Box Priors: A Robust Framework for Semi-Supervised Segmentation WACV 2022 "Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach NIPS 2022 SAViT: Structure-Aware Vision Transformer Pruning via Collaborative Optimization NIPS 2022 CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion ACL 2022 End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding ACL 2022 Perform like an Engine: A Closed-Loop Neural-Symbolic Learning Framework for Knowledge Graph Inference COLING 2022 Read Extensively, Focus Smartly: A Cross-document Semantic Enhancement Method for Visual Documents NER COLING 2022 Forward Compatible Few-Shot Class-Incremental Learning CVPR 2022 Label Matching Semi-Supervised Object Detection CVPR 2022 Slimmable Domain Adaptation CVPR 2022 Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression CVPR 2022 FAM: Visual Explanations for the Feature Representations From Deep Convolutional Networks CVPR 2022 Towards Comprehensive Representation Enhancement in Semantics-Guided Self-Supervised Monocular Depth Estimation ECCV 2022 FBNet: Feedback Network for Point Cloud Completion ECCV 2022 Enhancing Multi-modal Features Using Local Self-Attention for 3D Object Detection ECCV 2022 Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting ECCV 2022 Attention Diversification for Domain Generalization ECCV 2022 Learning Domain Adaptive Object Detection with Probabilistic Teacher ICML 2022 Can Abnormality be Detected by Graph Neural Networks? IJCAI 2022 A Deep One-Class Learning Method for Replay Attack Detection INTERSPEECH 2022 STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data NIPS 2021 Demodalizing Face Recognition with Synthetic Samples AAAI 2021 Self-Domain Adaptation for Face Anti-Spoofing AAAI 2021 MANGO: A Mask Attention Guided One-Stage Scene Text Spotter AAAI 2021 Towards Robust Model Reuse in the Presence of Latent Domains IJCAI 2021 Entity Concept-enhanced Few-shot Relation Extraction IJCNLP 2021 Divide-and-Assemble: Learning Block-Wise Memory for Unsupervised Anomaly Detection ICCV 2021 SGMNet: Learning Rotation-Invariant Point Cloud Representations via Sorted Gram Matrix ICCV 2021 RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation ICCV 2021 TransForensics: Image Forgery Localization With Dense Self-Attention ICCV 2021 Entity Concept-enhanced Few-shot Relation Extraction ACL 2021 A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data AAAI 2021 SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition AAAI 2021 RangeIoUDet: Range Image Based Real-Time 3D Object Detector Optimized by Intersection Over Union CVPR 2021 Learning Open Set Network with Discriminative Reciprocal Points ECCV 2020 AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding EMNLP 2020 Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting AAAI 2020 Spatio-Temporal Deformable Convolution for Compressed Video Quality Enhancement AAAI 2020 Neural Inheritance Relation Guided One-Shot Layer Assignment Search AAAI 2020 Counterfactual Samples Synthesizing for Robust Visual Question Answering CVPR 2020 A Layer Decomposition-Recomposition Framework for Neuron Pruning towards Accurate Lightweight Networks AAAI 2019 Learning Incremental Triplet Margin for Person Re-Identification AAAI 2019 An End-to-End Audio Classification System Based on Raw Waveforms and Mix-Training Strategy INTERSPEECH 2019 Counterfactual Critic Multi-Agent Training for Scene Graph Generation ICCV 2019 All You Need Is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification CVPR 2019 Collaborative Spatiotemporal Feature Learning for Video Action Recognition CVPR 2019 Cross-Relation Cross-Bag Attention for Distantly-Supervised Relation Extraction AAAI 2019 Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection AAAI 2019 Posterior-regularized REINFORCE for Instance Selection in Distant Supervision NAACL 2019 Extreme Network Compression via Filter Group Approximation ECCV 2018 Small-scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation ECCV 2018 AON: Towards Arbitrarily-Oriented Text Recognition CVPR 2018 Multi-Turn Video Question Answering via Multi-Stream Hierarchical Attention Context Network IJCAI 2018 Edit Probability for Scene Text Recognition CVPR 2018 Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation IJCAI 2018 All You Need Is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks With Orthonormality and Modulation CVPR 2017 Focusing Attention: Towards Accurate Text Recognition in Natural Images ICCV 2017