18 citations · 99 across the 19 of their papers we have counts for
19 papers
Vision-Language Dataset Distillation
Xindi Wu, Byron Zhang, Zhiwei Deng +1
Dataset distillation methods reduce large-scale datasets to smaller sets of synthetic data, preserving sufficient information to quickly train a new model from scratch. However, pr…
Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy
Shibo Jie, Haoqing Wang, Zhi-Hong Deng
Current state-of-the-art results in computer vision depend in part on fine-tuning large pre-trained vision models. However, with the exponential growth of model sizes, the conventi…
Masked Image Modeling with Local Multi-Scale Reconstruction
Haoqing Wang, Yehui Tang, Yunhe Wang +3
Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow lea…
Boundary Guided Learning-Free Semantic Control with Diffusion Models
Ye Zhu, Yu Wu, Zhiwei Deng +2
Applying pre-trained generative denoising diffusion models (DDMs) for downstream tasks such as image semantic editing usually requires either fine-tuning DDMs or learning auxiliary…
Global-to-local Expression-aware Embeddings for Facial Action Unit Detection
Rudong An, Wei Zhang, Hao Zeng +3
Expressions and facial action units (AUs) are two levels of facial behavior descriptors. Expression auxiliary information has been widely used to improve the AU detection performan…
Facial Action Units Detection Aided by Global-Local Expression Embedding
Zhipeng Hu, Wei Zhang, Lincheng Li +4
Since Facial Action Unit (AU) annotations require domain expertise, common AU datasets only contain a limited number of subjects. As a result, a crucial challenge for AU detection…
Rethinking Minimal Sufficient Representation in Contrastive Learning
Haoqing Wang, Xun Guo, Zhi-Hong Deng +1
Contrastive learning between different views of the data achieves outstanding success in the field of self-supervised representation learning and the learned representations are us…
GSR: Global Graph Guided Session-based Recommendation
Zhi-Hong Deng, Chang-Dong Wang, Ling Huang +2
Session-based recommendation tries to make use of anonymous session data to deliver high-quality recommendation under the condition that user-profiles and the complete historical b…
Adaptive Appearance Rendering
Mengyao Zhai, Ruizhi Deng, Jiacheng Chen +3
We propose an approach to generate images of people given a desired appearance and pose. Disentangled representations of pose and appearance are necessary to handle the compound va…
Policy Message Passing: A New Algorithm for Probabilistic Graph Inference
Zhiwei Deng, Greg Mori
A general graph-structured neural network architecture operates on graphs through two core components: (1) complex enough message functions; (2) a fixed information aggregation pro…
Continuous Graph Flow
Zhiwei Deng, Megha Nawhal, Lili Meng +1
In this paper, we propose Continuous Graph Flow, a generative continuous flow based method that aims to model complex distributions of graph-structured data. Once learned, the mode…
Structured Label Inference for Visual Understanding
Nelson Nauata, Hexiang Hu, Guang-Tong Zhou +3
Visual data such as images and videos contain a rich source of structured semantic labels as well as a wide range of interacting components. Visual content could be assigned with f…
Active Learning for Structured Prediction from Partially Labeled Data
Mehran Khodabandeh, Zhiwei Deng, Mostafa S. Ibrahim +2
We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or v…
Generic Tubelet Proposals for Action Localization
Jiawei He, Mostafa S. Ibrahim, Zhiwei Deng +1
We develop a novel framework for action localization in videos. We propose the Tube Proposal Network (TPN), which can generate generic, class-independent, video-level tubelet propo…
LabelBank: Revisiting Global Perspectives for Semantic Segmentation
Hexiang Hu, Zhiwei Deng, Guang-Tong Zhou +2
Semantic segmentation requires a detailed labeling of image pixels by object category. Information derived from local image patches is necessary to describe the detailed shape of i…
Hierarchical Deep Temporal Models for Group Activity Recognition
Mostafa S. Ibrahim, Srikanth Muralidharan, Zhiwei Deng +2
In this paper we present an approach for classifying the activity performed by a group of people in a video sequence. This problem of group activity recognition can be addressed by…
Learning Structured Inference Neural Networks with Label Relations
Hexiang Hu, Guang-Tong Zhou, Zhiwei Deng +2
Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible. A natural image could be assigned with fine-grained…
Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition
Zhiwei Deng, Arash Vahdat, Hexiang Hu +1
Rich semantic relations are important in a variety of visual recognition problems. As a concrete example, group activity recognition involves the interactions and relative spatial…
Deep Structured Models For Group Activity Recognition
Zhiwei Deng, Mengyao Zhai, Lei Chen +4
This paper presents a deep neural-network-based hierarchical graphical model for individual and group activity recognition in surveillance scenes. Deep networks are used to recogni…