80 citations · 455 across the 39 of their papers we have counts for
40 papers
Image Captioning via Dynamic Path Customization
Yiwei Ma, Jiayi Ji, Xiaoshuai Sun +4
This paper explores a novel dynamic network for vision and language tasks, where the inferring structure is customized on the fly for different inputs. Most previous state-of-the-a…
Latent Feature Relation Consistency for Adversarial Robustness
Xingbin Liu, Huafeng Kuang, Hong Liu +3
Deep neural networks have been applied in many computer vision tasks and achieved state-of-the-art performance. However, misclassification will occur when DNN predicts adversarial…
CAT:Collaborative Adversarial Training
Xingbin Liu, Huafeng Kuang, Xianming Lin +2
Adversarial training can improve the robustness of neural networks. Previous methods focus on a single adversarial training strategy and do not consider the model property trained…
Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification
Jiaer Xia, Lei Tan, Pingyang Dai +3
Occluded person re-identification (Re-ID) aims to address the potential occlusion problem when matching occluded or holistic pedestrians from different camera views. Many methods u…
Spectral Aware Softmax for Visible-Infrared Person Re-Identification
Lei Tan, Pingyang Dai, Qixiang Ye +3
Visible-infrared person re-identification (VI-ReID) aims to match specific pedestrian images from different modalities. Although suffering an extra modality discrepancy, existing m…
Exploring Invariant Representation for Visible-Infrared Person Re-Identification
Lei Tan, Yukang Zhang, Shengmei Shen +5
Cross-spectral person re-identification, which aims to associate identities to pedestrians across different spectra, faces a main challenge of the modality discrepancy. In this pap…
Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning
Qiong Wu, Jiahan Li, Pingyang Dai +4
Unsupervised domain adaptation person re-identification (Re-ID) aims to identify pedestrian images within an unlabeled target domain with an auxiliary labeled source-domain dataset…
Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network
Haowei Wang, Jiayi Ji, Yiyi Zhou +2
Panoptic Narrative Grounding (PNG) is an emerging cross-modal grounding task, which locates the target regions of an image corresponding to the text description. Existing approache…
CycleTrans: Learning Neutral yet Discriminative Features for Visible-Infrared Person Re-Identification
Qiong Wu, Jiaer Xia, Pingyang Dai +3
Visible-infrared person re-identification (VI-ReID) is a task of matching the same individuals across the visible and infrared modalities. Its main challenge lies in the modality g…
Dynamic Prototype Mask for Occluded Person Re-Identification
Lei Tan, Pingyang Dai, Rongrong Ji +1
Although person re-identification has achieved an impressive improvement in recent years, the common occlusion case caused by different obstacles is still an unsettled issue in rea…
Learning Best Combination for Efficient N:M Sparsity
Yuxin Zhang, Mingbao Lin, Zhihang Lin +5
By forcing at most N out of M consecutive weights to be non-zero, the recent N:M network sparsity has received increasing attention for its two attractive advantages: 1) Promising…
Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks
Gen Luo, Yiyi Zhou, Xiaoshuai Sun +5
Despite the exciting performance, Transformer is criticized for its excessive parameters and computation cost. However, compressing Transformer remains as an open problem due to it…
Global2Local: A Joint-Hierarchical Attention for Video Captioning
Chengpeng Dai, Fuhai Chen, Xiaoshuai Sun +3
Recently, automatic video captioning has attracted increasing attention, where the core challenge lies in capturing the key semantic items, like objects and actions as well as thei…
Differentiated Relevances Embedding for Group-based Referring Expression Comprehension
Fuhai Chen, Xuri Ge, Xiaoshuai Sun +4
The key of referring expression comprehension lies in capturing the cross-modal visual-linguistic relevance. Existing works typically model the cross-modal relevance in each image,…
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks
Yunshan Zhong, Mingbao Lin, Xunchao Li +5
Light-weight super-resolution (SR) models have received considerable attention for their serviceability in mobile devices. Many efforts employ network quantization to compress SR m…
CF-ViT: A General Coarse-to-Fine Method for Vision Transformer
Mengzhao Chen, Mingbao Lin, Ke Li +4
Vision Transformers (ViT) have made many breakthroughs in computer vision tasks. However, considerable redundancy arises in the spatial dimension of an input image, leading to mass…
Towards Language-guided Visual Recognition via Dynamic Convolutions
Gen Luo, Yiyi Zhou, Xiaoshuai Sun +3
In this paper, we are committed to establishing an unified and end-to-end multi-modal network via exploring the language-guided visual recognition. To approach this target, we firs…
OMPQ: Orthogonal Mixed Precision Quantization
Yuexiao Ma, Taisong Jin, Xiawu Zheng +6
To bridge the ever increasing gap between deep neural networks' complexity and hardware capability, network quantization has attracted more and more research attention. The latest…
Fine-grained Data Distribution Alignment for Post-Training Quantization
Yunshan Zhong, Mingbao Lin, Mengzhao Chen +5
While post-training quantization receives popularity mostly due to its evasion in accessing the original complete training dataset, its poor performance also stems from scarce imag…
HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
Yuhan Wang, Xu Chen, Junwei Zhu +7
In this work, we propose a high fidelity face swapping method, called HifiFace, which can well preserve the face shape of the source face and generate photo-realistic results. Unli…
Black-Box Dissector: Towards Erasing-based Hard-Label Model Stealing Attack
Yixu Wang, Jie Li, Hong Liu +4
Previous studies have verified that the functionality of black-box models can be stolen with full probability outputs. However, under the more practical hard-label setting, we obse…
Carrying out CNN Channel Pruning in a White Box
Yuxin Zhang, Mingbao Lin, Chia-Wen Lin +5
Channel Pruning has been long studied to compress CNNs, which significantly reduces the overall computation. Prior works implement channel pruning in an unexplainable manner, which…
Lottery Jackpots Exist in Pre-trained Models
Yuxin Zhang, Mingbao Lin, Yunshan Zhong +2
Network pruning is an effective approach to reduce network complexity with acceptable performance compromise. Existing studies achieve the sparsity of neural networks via time-cons…
Image-to-image Translation via Hierarchical Style Disentanglement
Xinyang Li, Shengchuan Zhang, Jie Hu +6
Recently, image-to-image translation has made significant progress in achieving both multi-label (\ie, translation conditioned on different labels) and multi-style (\ie, generation…