29 citations · 91 across the 16 of their papers we have counts for
20 papers
WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data
Ziheng Zhang, Yunzhong Hou, Naijing Liu +1
This paper introduces WARDEN, an early language model system capable of transcribing and translating Wardaman, an endangered Australian indigenous language into English. The signif…
Extreme Amodal Face Detection
Changlin Song, Yunzhong Hou, Michael Randall Barnes +2
Extreme amodal detection is the task of inferring the 2D location of objects that are not fully visible in the input image but are visible within an expanded field-of-view. This di…
Effective Training Data Synthesis for Improving MLLM Chart Understanding
Yuwei Yang, Zeyu Zhang, Yunzhong Hou +5
Being able to effectively read scientific plots, or chart understanding, is a central part toward building effective agents for science. However, existing multimodal large language…
REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
Xingjian Leng, Jaskirat Singh, Yunzhong Hou +3
In this paper we tackle a fundamental question: "Can we train latent diffusion models together with the variational auto-encoder (VAE) tokenizer in an end-to-end manner?" Tradition…
Learning Camera Movement Control from Real-World Drone Videos
Yunzhong Hou, Liang Zheng, Philip Torr
This study seeks to automate camera movement control for filming existing subjects into attractive videos, contrasting with the creation of non-existent content by directly generat…
Optimizing Camera Configurations for Multi-View Pedestrian Detection
Yunzhong Hou, Xingjian Leng, Tom Gedeon +1
Jointly considering multiple camera views (multi-view) is very effective for pedestrian detection under occlusion. For such multi-view systems, it is critical to have well-designed…
Learning to Select Camera Views: Efficient Multiview Understanding at Few Glances
Yunzhong Hou, Stephen Gould, Liang Zheng
Multiview camera setups have proven useful in many computer vision applications for reducing ambiguities, mitigating occlusions, and increasing field-of-view coverage. However, the…
Learning to Structure an Image with Few Colors and Beyond
Yunzhong Hou, Liang Zheng, Stephen Gould
Color and structure are the two pillars that combine to give an image its meaning. Interested in critical structures for neural network recognition, we isolate the influence of col…
Multi-View Correlation Consistency for Semi-Supervised Semantic Segmentation
Yunzhong Hou, Stephen Gould, Liang Zheng
Semi-supervised semantic segmentation needs rich and robust supervision on unlabeled data. Consistency learning enforces the same pixel to have similar features in different augmen…
Adaptive Affinity for Associations in Multi-Target Multi-Camera Tracking
Yunzhong Hou, Zhongdao Wang, Shengjin Wang +1
Data associations in multi-target multi-camera tracking (MTMCT) usually estimate affinity directly from re-identification (re-ID) feature distances. However, we argue that it might…
Critical local well-posedness for the fully nonlinear Peskin problem
Stephen Cameron, Robert M. Strain
We study the problem where a one-dimensional elastic string is immersed in a two-dimensional steady Stokes fluid. This is known as the Stokes immersed boundary problem and also as…
Ranking Models in Unlabeled New Environments
Xiaoxiao Sun, Yunzhong Hou, Weijian Deng +2
Consider a scenario where we are supplied with a number of ready-to-use models trained on a certain source domain and hope to directly apply the most appropriate ones to different…
Memory-Free Generative Replay For Class-Incremental Learning
Xiaomeng Xin, Yiran Zhong, Yunzhong Hou +2
Regularization-based methods are beneficial to alleviate the catastrophic forgetting problem in class-incremental learning. With the absence of old task images, they often assume t…
Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)
Yunzhong Hou, Liang Zheng
Multiview detection incorporates multiple camera views to deal with occlusions, and its central problem is multiview aggregation. Given feature map projections from multiple views…
Visualizing Adapted Knowledge in Domain Transfer
Yunzhong Hou, Liang Zheng
A source model trained on source data and a target model learned through unsupervised domain adaptation (UDA) usually encode different knowledge. To understand the adaptation proce…
Source Free Domain Adaptation with Image Translation
Yunzhong Hou, Liang Zheng
Effort in releasing large-scale datasets may be compromised by privacy and intellectual property considerations. A feasible alternative is to release pre-trained models instead. Wh…
Multiview Detection with Feature Perspective Transformation
Yunzhong Hou, Liang Zheng, Stephen Gould
Incorporating multiple camera views for detection alleviates the impact of occlusions in crowded scenes. In a multiview system, we need to answer two important questions when deali…
Learning to Structure an Image with Few Colors
Yunzhong Hou, Liang Zheng, Stephen Gould
Color and structure are the two pillars that construct an image. Usually, the structure is well expressed through a rich spectrum of colors, allowing objects in an image to be reco…
Locality Aware Appearance Metric for Multi-Target Multi-Camera Tracking
Yunzhong Hou, Liang Zheng, Zhongdao Wang +1
Multi-target multi-camera tracking (MTMCT) systems track targets across cameras. Due to the continuity of target trajectories, tracking systems usually restrict their data associat…
Improving Device-Edge Cooperative Inference of Deep Learning via 2-Step Pruning
Wenqi Shi, Yunzhong Hou, Sheng Zhou +3
Deep neural networks (DNNs) are state-of-the-art solutions for many machine learning applications, and have been widely used on mobile devices. Running DNNs on resource-constrained…