295 citations · 1.1k across the 36 of their papers we have counts for
37 papers
Enhanced Graph Transformer with Serialized Graph Tokens
Ruixiang Wang, Yuyang Hong, Shiming Xiang +1
Transformers have demonstrated success in graph learning, particularly for node-level tasks. However, existing methods encounter an information bottleneck when generating graph-lev…
IF-Bench: Benchmarking and Enhancing MLLMs for Infrared Images with Generative Visual Prompting
Tao Zhang, Yuyang Hong, Yang Xia +5
Recent advances in multimodal large language models (MLLMs) have led to impressive progress across various benchmarks. However, their capability in understanding infrared images re…
Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization
Tao Zhang, Cheng Da, Kun Ding +7
Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level rewar…
Weak Distribution Detectors Lead to Stronger Generalizability of Vision-Language Prompt Tuning
Kun Ding, Haojian Zhang, Qiang Yu +3
We propose a generalized method for boosting the generalization ability of pre-trained vision-language models (VLMs) while fine-tuning on downstream few-shot tasks. The idea is rea…
Reusable Architecture Growth for Continual Stereo Matching
Chenghao Zhang, Gaofeng Meng, Bin Fan +4
The remarkable performance of recent stereo depth estimation models benefits from the successful use of convolutional neural networks to regress dense disparity. Akin to most tasks…
Compositional Kronecker Context Optimization for Vision-Language Models
Kun Ding, Xiaohui Li, Qiang Yu +3
Context Optimization (CoOp) has emerged as a simple yet effective technique for adapting CLIP-like vision-language models to downstream image recognition tasks. Nevertheless, learn…
PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Images
Tao Zhang, Kun Ding, Jinyong Wen +4
Self-supervised learning (SSL) for RGB images has achieved significant success, yet there is still limited research on SSL for infrared images, primarily due to three prominent cha…
Free Lunch for Generating Effective Outlier Supervision
Sen Pei, Jiaxi Sun, Richard Yi Da Xu +3
When deployed in practical applications, computer vision systems will encounter numerous unexpected images (\emph{i.e.}, out-of-distribution data). Due to the potentially raised sa…
Pro-tuning: Unified Prompt Tuning for Vision Tasks
Xing Nie, Bolin Ni, Jianlong Chang +6
In computer vision, fine-tuning is the de-facto approach to leverage pre-trained vision models to perform downstream tasks. However, deploying it in practice is quite challenging,…
Expanding Language-Image Pretrained Models for General Video Recognition
Bolin Ni, Houwen Peng, Minghao Chen +5
Contrastive language-image pretraining has shown great success in learning visual-textual joint representation from web-scale data, demonstrating remarkable "zero-shot" generalizat…
Prompt Tuning with Soft Context Sharing for Vision-Language Models
Kun Ding, Ying Wang, Pengzhang Liu +4
Vision-language models have recently shown great potential on many tasks in computer vision. Meanwhile, prior work demonstrates prompt tuning designed for vision-language models co…
Domain Decorrelation with Potential Energy Ranking
Sen Pei, Jiaxi Sun, Richard Yi Da Xu +2
Machine learning systems, especially the methods based on deep learning, enjoy great success in modern computer vision tasks under experimental settings. Generally, these classic d…
Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction
Kailun Wu, Zhangming Chan, Weijie Bian +5
Exploration-Exploitation (E{\&}E) algorithms are commonly adopted to deal with the feedback-loop issue in large-scale online recommender systems. Most of existing studies believe t…
HAN: An Efficient Hierarchical Self-Attention Network for Skeleton-Based Gesture Recognition
Jianbo Liu, Ying Wang, Shiming Xiang +1
Previous methods for skeleton-based gesture recognition mostly arrange the skeleton sequence into a pseudo picture or spatial-temporal graph and apply deep Convolutional Neural Net…
CAN: Feature Co-Action for Click-Through Rate Prediction
Weijie Bian, Kailun Wu, Lejian Ren +12
Feature interaction has been recognized as an important problem in machine learning, which is also very essential for click-through rate (CTR) prediction tasks. In recent years, De…
Dynamic Scale Training for Object Detection
Yukang Chen, Peizhen Zhang, Zeming Li +5
We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Previous strategies like image pyramid, multi-scale tra…
Precipitation Forecasting via Multi-Scale Deconstructed ConvLSTM
Xinyu Xiao, Qiuming Kuang, Shiming Xiang +2
Numerical Weather Prediction (NWP), is widely used in precipitation forecasting, based on complex equations of atmospheric motion requires supercomputers to infer the state of the…
AugFPN: Improving Multi-scale Feature Learning for Object Detection
Chaoxu Guo, Bin Fan, Qian Zhang +2
Current state-of-the-art detectors typically exploit feature pyramid to detect objects at different scales. Among them, FPN is one of the representative works that build a feature…
Learning Where to Focus for Efficient Video Object Detection
Zhengkai Jiang, Yu Liu, Ceyuan Yang +5
Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous a…
FontGAN: A Unified Generative Framework for Chinese Character Stylization and De-stylization
Xiyan Liu, Gaofeng Meng, Shiming Xiang +1
Chinese character synthesis involves two related aspects, i.e., style maintenance and content consistency. Although some methods have achieved remarkable success in synthesizing a…
DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing
Yongcheng Liu, Bin Fan, Gaofeng Meng +3
Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable. A thorough grasp of the elusive shape requires sufficientl…
Relation-Shape Convolutional Neural Network for Point Cloud Analysis
Yongcheng Liu, Bin Fan, Shiming Xiang +1
Point cloud analysis is very challenging, as the shape implied in irregular points is difficult to capture. In this paper, we propose RS-CNN, namely, Relation-Shape Convolutional N…
Differentiable Architecture Search with Ensemble Gumbel-Softmax
Jianlong Chang, Xinbang Zhang, Yiwen Guo +3
For network architecture search (NAS), it is crucial but challenging to simultaneously guarantee both effectiveness and efficiency. Towards achieving this goal, we develop a differ…
Deep Discriminative Clustering Analysis
Jianlong Chang, Yiwen Guo, Lingfeng Wang +3
Traditional clustering methods often perform clustering with low-level indiscriminative representations and ignore relationships between patterns, resulting in slight achievements…