325 citations · 2k across the 89 of their papers we have counts for
21 papers · 1 filter
GMFlow: Learning Optical Flow via Global Matching
Haofei Xu, Jing Zhang, Jianfei Cai +2
Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations…
Pruning Self-attentions into Convolutional Layers in Single Path
Haoyu He, Jianfei Cai, Jing Liu +4
Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. However, modeling global correlations with multi-head self-attention (MSA) layer…
Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation
Chuang Lin, Yi Jiang, Jianfei Cai +3
Vision-and-Language Navigation (VLN) is a task that an agent is required to follow a language instruction to navigate to the goal position, which relies on the ongoing interactions…
CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing
Daxuan Ren, Jianmin Zheng, Jianfei Cai +8
Generating an interpretable and compact representation of 3D shapes from point clouds is an important and challenging problem. This paper presents CSG-Stump Net, an unsupervised en…
Auto-Parsing Network for Image Captioning and Visual Question Answering
Xu Yang, Chongyang Gao, Hanwang Zhang +1
We propose an Auto-Parsing Network (APN) to discover and exploit the input data's hidden tree structures for improving the effectiveness of the Transformer-based vision-language sy…
Semantic Compositional Learning for Low-shot Scene Graph Generation
Tao He, Lianli Gao, Jingkuan Song +2
Scene graphs provide valuable information to many downstream tasks. Many scene graph generation (SGG) models solely use the limited annotated relation triples for training, leading…
Learning Meta-class Memory for Few-Shot Semantic Segmentation
Zhonghua Wu, Xiangxi Shi, Guosheng lin +1
Currently, the state-of-the-art methods treat few-shot semantic segmentation task as a conditional foreground-background segmentation problem, assuming each class is independent. I…
Remember What You have drawn: Semantic Image Manipulation with Memory
Xiangxi Shi, Zhonghua Wu, Guosheng Lin +2
Image manipulation with natural language, which aims to manipulate images with the guidance of language descriptions, has been a challenging problem in the fields of computer visio…
Multi-Label Image Classification with Contrastive Learning
Son D. Dao, Ethan Zhao, Dinh Phung +1
Recently, as an effective way of learning latent representations, contrastive learning has been increasingly popular and successful in various domains. The success of constrastive…
Towards Unbiased Visual Emotion Recognition via Causal Intervention
Yuedong Chen, Xu Yang, Tat-Jen Cham +1
Although much progress has been made in visual emotion recognition, researchers have realized that modern deep networks tend to exploit dataset characteristics to learn spurious st…
Half-body Portrait Relighting with Overcomplete Lighting Representation
Guoxian Song, Tat-Jen Cham, Jianfei Cai +1
We present a neural-based model for relighting a half-body portrait image by simply referring to another portrait image with the desired lighting condition. Rather than following c…
RSG: A Simple but Effective Module for Learning Imbalanced Datasets
Jianfeng Wang, Thomas Lukasiewicz, Xiaolin Hu +2
Imbalanced datasets widely exist in practice and area great challenge for training deep neural models with agood generalization on infrequent classes. In this work, wepropose a new…
Less is More: Pay Less Attention in Vision Transformers
Zizheng Pan, Bohan Zhuang, Haoyu He +2
Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. Howe…
End-to-end One-shot Human Parsing
Haoyu He, Bohan Zhuang, Jing Zhang +2
Previous human parsing methods are limited to parsing humans into pre-defined classes, which is inflexible for practical fashion applications that often have new fashion item class…
Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition
Chuanxia Zheng, Duy-Son Dao, Guoxian Song +2
Existing scene understanding systems mainly focus on recognizing the visible parts of a scene, ignoring the intact appearance of physical objects in the real-world. Concurrently, i…
The Spatially-Correlative Loss for Various Image Translation Tasks
Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai
We propose a novel spatially-correlative loss that is simple, efficient and yet effective for preserving scene structure consistency while supporting large appearance changes durin…
High-Resolution Optical Flow from 1D Attention and Correlation
Haofei Xu, Jiaolong Yang, Jianfei Cai +2
Optical flow is inherently a 2D search problem, and thus the computational complexity grows quadratically with respect to the search window, making large displacements matching inf…
Bridging Global Context Interactions for High-Fidelity Image Completion
Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai +1
Bridging global context interactions correctly is important for high-fidelity image completion with large masks. Previous methods attempting this via deep or large receptive field…
Causal Attention for Vision-Language Tasks
Xu Yang, Hanwang Zhang, Guojun Qi +1
We present a novel attention mechanism: Causal Attention (CATT), to remove the ever-elusive confounding effect in existing attention-based vision-language models. This effect cause…
Scalable Vision Transformers with Hierarchical Pooling
Zizheng Pan, Bohan Zhuang, Jing Liu +2
The recently proposed Visual image Transformers (ViT) with pure attention have achieved promising performance on image recognition tasks, such as image classification. However, the…
Semi-supervised Left Atrium Segmentation with Mutual Consistency Training
Yicheng Wu, Minfeng Xu, Zongyuan Ge +2
Semi-supervised learning has attracted great attention in the field of machine learning, especially for medical image segmentation tasks, since it alleviates the heavy burden of co…