362 citations · 1.3k across the 40 of their papers we have counts for
40 papers
Cross-domain Augmentation Networks for Click-Through Rate Prediction
Xu Chen, Zida Cheng, Shuai Xiao +2
Data sparsity is an important issue for click-through rate (CTR) prediction, particularly when user-item interactions is too sparse to learn a reliable model. Recently, many works…
Category-Oriented Representation Learning for Image to Multi-Modal Retrieval
Zida Cheng, Chen Ju, Shuai Xiao +5
The rise of multi-modal search requests from users has highlighted the importance of multi-modal retrieval (i.e. image-to-text or text-to-image retrieval), yet the more complex tas…
Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding
Fengyuan Shi, Ruopeng Gao, Weilin Huang +1
Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) s…
Cross-Architecture Self-supervised Video Representation Learning
Sheng Guo, Zihua Xiong, Yujie Zhong +4
In this paper, we present a new cross-architecture contrastive learning (CACL) framework for self-supervised video representation learning. CACL consists of a 3D CNN and a video tr…
InsCLR: Improving Instance Retrieval with Self-Supervision
Zelu Deng, Yujie Zhong, Sheng Guo +1
This work aims at improving instance retrieval with self-supervision. We find that fine-tuning using the recently developed self-supervised (SSL) learning methods, such as SimCLR a…
End-to-End Dense Video Grounding via Parallel Regression
Fengyuan Shi, Weilin Huang, Limin Wang
Video grounding aims to localize the corresponding video moment in an untrimmed video given a language query. Existing methods often address this task in an indirect way, by castin…
TOOD: Task-aligned One-stage Object Detection
Chengjian Feng, Yujie Zhong, Yu Gao +2
One-stage object detection is commonly implemented by optimizing two sub-tasks: object classification and localization, using heads with two parallel branches, which might lead to…
Exploring Classification Equilibrium in Long-Tailed Object Detection
Chengjian Feng, Yujie Zhong, Weilin Huang
The conventional detectors tend to make imbalanced classification and suffer performance drop, when the distribution of the training data is severely skewed. In this paper, we prop…
Mutually-aware Sub-Graphs Differentiable Architecture Search
Haoxian Tan, Sheng Guo, Yujie Zhong +2
Differentiable architecture search is prevalent in the field of NAS because of its simplicity and efficiency, where two paradigms, multi-path algorithms and single-path methods, ar…
Rethinking Deep Contrastive Learning with Embedding Memory
Haozhi Zhang, Xun Wang, Weilin Huang +1
Pair-wise loss functions have been extensively studied and shown to continuously improve the performance of deep metric learning (DML). However, they are primarily designed with in…
Brain Image Synthesis with Unsupervised Multivariate Canonical CSCNet
Yawen Huang, Feng Zheng, Danyang Wang +3
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition. However, obt…
Unchain the Search Space with Hierarchical Differentiable Architecture Search
Guanting Liu, Yujie Zhong, Sheng Guo +2
Differentiable architecture search (DAS) has made great progress in searching for high-performance architectures with reduced computational cost. However, DAS-based methods mainly…
Representation Sharing for Fast Object Detector Search and Beyond
Yujie Zhong, Zelu Deng, Sheng Guo +2
Region Proposal Network (RPN) provides strong support for handling the scale variation of objects in two-stage object detection. For one-stage detectors which do not have RPN, it i…
Deformable Siamese Attention Networks for Visual Object Tracking
Yuechen Yu, Yilei Xiong, Weilin Huang +1
Siamese-based trackers have achieved excellent performance on visual object tracking. However, the target template is not updated online, and the features of the target template an…
Channel Interaction Networks for Fine-Grained Image Categorization
Yu Gao, Xintong Han, Xun Wang +2
Fine-grained image categorization is challenging due to the subtle inter-class differences.We posit that exploiting the rich relationships between channels can help capture such di…
iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection
Chenfan Zhuang, Xintong Han, Weilin Huang +1
Training an object detector on a data-rich domain and applying it to a data-poor one with limited performance drop is highly attractive in industry, because it saves huge annotatio…
Knowledge Integration Networks for Action Recognition
Shiwen Zhang, Sheng Guo, Limin Wang +2
In this work, we propose Knowledge Integration Networks (referred as KINet) for video action recognition. KINet is capable of aggregating meaningful context features which are of g…
V4D:4D Convolutional Neural Networks for Video-level Representation Learning
Shiwen Zhang, Sheng Guo, Weilin Huang +2
Most existing 3D CNNs for video representation learning are clip-based methods, and thus do not consider video-level temporal evolution of spatio-temporal features. In this paper,…
Cross-Batch Memory for Embedding Learning
Xun Wang, Haozhi Zhang, Weilin Huang +1
Mining informative negative instances are of central importance to deep metric learning (DML), however this task is intrinsically limited by mini-batch training, where only a mini-…
Convolutional Character Networks
Linjie Xing, Zhi Tian, Weilin Huang +1
Recent progress has been made on developing a unified framework for joint text detection and recognition in natural images, but existing joint models were mostly built on two-stage…
Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation
Weifeng Ge, Sheng Guo, Weilin Huang +1
Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only. Unlike previous methods which are composed of multiple…
Dual-Stream Pyramid Registration Network
Miao Kang, Xiaojun Hu, Weilin Huang +2
We propose a Dual-Stream Pyramid Registration Network (referred as Dual-PRNet) for unsupervised 3D medical image registration. Unlike recent CNN-based registration approaches, such…
The iMaterialist Fashion Attribute Dataset
Sheng Guo, Weilin Huang, Xiao Zhang +6
Large-scale image databases such as ImageNet have significantly advanced image classification and other visual recognition tasks. However much of these datasets are constructed onl…
Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning
Xun Wang, Xintong Han, Weilin Huang +2
A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad of solutions for deep metric learning. In this paper, we prov…