7 citations · 43 across the 15 of their papers we have counts for
15 papers
Attribute-Prompted Kernel Hashing for Unsupervised Data-Efficient Cross-Modal Retrieval
Runhao Li, Xiaoxu Ma, Zhenyu Weng +5
Unsupervised cross-modal hashing enables efficient retrieval of semantically related instances across different modalities without requiring manual semantic annotation. However, ex…
Unsupervised Data-Efficient Cross-Modal Retrieval with Global-Neighborhood Alignment Hashing
Runhao Li, Xiaoxu Ma, Zhenyu Weng +5
Compared to supervised cross-modal hashing (CMH), unsupervised CMH reduces the reliance on manual labeling by learning binary codes from unlabeled image-text pairs. However, existi…
HOI-aware Adaptive Network for Weakly-supervised Action Segmentation
Runzhong Zhang, Suchen Wang, Yueqi Duan +3
In this paper, we propose an HOI-aware adaptive network named AdaAct for weakly-supervised action segmentation. Most existing methods learn a fixed network to predict the action of…
Ambiguity-aware Point Cloud Segmentation by Adaptive Margin Contrastive Learning
Yang Chen, Yueqi Duan, Haowen Sun +2
This paper proposes an adaptive margin contrastive learning method for 3D semantic segmentation on point clouds. Most existing methods use equally penalized objectives, which ignor…
PointVDP: Learning View-Dependent Projection by Fireworks Rays for 3D Point Cloud Segmentation
Yang Chen, Yueqi Duan, Haowen Sun +3
In this paper, we propose view-dependent projection (VDP) to facilitate point cloud segmentation, designing efficient 3D-to-2D mapping that dynamically adapts to the spatial geomet…
Adaptive Margin Contrastive Learning for Ambiguity-aware 3D Semantic Segmentation
Yang Chen, Yueqi Duan, Runzhong Zhang +1
In this paper, we propose an adaptive margin contrastive learning method for 3D point cloud semantic segmentation, namely AMContrast3D. Most existing methods use equally penalized…
POAR: Towards Open Vocabulary Pedestrian Attribute Recognition
Yue Zhang, Suchen Wang, Shichao Kan +3
Pedestrian attribute recognition (PAR) aims to predict the attributes of a target pedestrian in a surveillance system. Existing methods address the PAR problem by training a multi-…
Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger
Yi Yu, Yufei Wang, Wenhan Yang +3
Recent deep-learning-based compression methods have achieved superior performance compared with traditional approaches. However, deep learning models have proven to be vulnerable t…
Temporal Coherent Test-Time Optimization for Robust Video Classification
Chenyu Yi, Siyuan Yang, Yufei Wang +3
Deep neural networks are likely to fail when the test data is corrupted in real-world deployment (e.g., blur, weather, etc.). Test-time optimization is an effective way that adapts…
Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond
Yi Yu, Wenhan Yang, Yap-Peng Tan +1
Rain removal aims to remove rain streaks from images/videos and reduce the disruptive effects caused by rain. It not only enhances image/video visibility but also allows many compu…
Benchmarking the Robustness of Spatial-Temporal Models Against Corruptions
Chenyu Yi, Siyuan Yang, Haoliang Li +2
The state-of-the-art deep neural networks are vulnerable to common corruptions (e.g., input data degradations, distortions, and disturbances caused by weather changes, system error…
Attention-Aware Noisy Label Learning for Image Classification
Zhenzhen Wang, Chunyan Xu, Yap-Peng Tan +1
Deep convolutional neural networks (CNNs) learned on large-scale labeled samples have achieved remarkable progress in computer vision, such as image/video classification. The cheap…
Scaling Object Detection by Transferring Classification Weights
Jason Kuen, Federico Perazzi, Zhe Lin +2
Large scale object detection datasets are constantly increasing their size in terms of the number of classes and annotations count. Yet, the number of object-level categories annot…
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
Jason Kuen, Xiangfei Kong, Zhe Lin +4
It is desirable to train convolutional networks (CNNs) to run more efficiently during inference. In many cases however, the computational budget that the system has for inference c…
DelugeNets: Deep Networks with Efficient and Flexible Cross-layer Information Inflows
Jason Kuen, Xiangfei Kong, Gang Wang +1
Deluge Networks (DelugeNets) are deep neural networks which efficiently facilitate massive cross-layer information inflows from preceding layers to succeeding layers. The connectio…