50 citations · 123 across the 14 of their papers we have counts for
15 papers
3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation
Yi Zhang, Pengliang Ji, Angtian Wang +3
Regression-based methods for 3D human pose estimation directly predict the 3D pose parameters from a 2D image using deep networks. While achieving state-of-the-art performance on s…
Cross-Modal Concept Learning and Inference for Vision-Language Models
Yi Zhang, Ce Zhang, Yushun Tang +1
Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP, establish the correlation between texts and images, achieving remarkable success on various downstream tasks wi…
From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping
Junyang Wang, Ming Yan, Yi Zhang +1
With the development of Vision-Language Pre-training Models (VLPMs) represented by CLIP and ALIGN, significant breakthroughs have been achieved for association-based visual tasks s…
What Makes Convolutional Models Great on Long Sequence Modeling?
Yuhong Li, Tianle Cai, Yi Zhang +2
Convolutional models have been widely used in multiple domains. However, most existing models only use local convolution, making the model unable to handle long-range dependency ef…
Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation
Qihao Liu, Yi Zhang, Song Bai +1
Occlusion poses a great threat to monocular multi-person 3D human pose estimation due to large variability in terms of the shape, appearance, and position of occluders. While exist…
Two-Stage Fine-Tuning: A Novel Strategy for Learning Class-Imbalanced Data
Taha ValizadehAslani, Yiwen Shi, Jing Wang +5
Classification on long-tailed distributed data is a challenging problem, which suffers from serious class-imbalance and hence poor performance on tail classes with only a few sampl…
Nuisance-Label Supervision: Robustness Improvement by Free Labels
Xinyue Wei, Weichao Qiu, Yi Zhang +2
In this paper, we present a Nuisance-label Supervision (NLS) module, which can make models more robust to nuisance factor variations. Nuisance factors are those irrelevant to a tas…
Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning
Yi Zhang, Sheng Huang, Xi Peng +1
Data augmentation is a powerful technique for improving the performance of the few-shot classification task. It generates more samples as supplements, and then this task can be tra…
Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
Yingda Xia, Yi Zhang, Fengze Liu +2
The ability to detect failures and anomalies are fundamental requirements for building reliable systems for computer vision applications, especially safety-critical applications of…
Identity Preserve Transform: Understand What Activity Classification Models Have Learnt
Jialing Lyu, Weichao Qiu, Xinyue Wei +3
Activity classification has observed great success recently. The performance on small dataset is almost saturated and people are moving towards larger datasets. What leads to the p…
RSA: Randomized Simulation as Augmentation for Robust Human Action Recognition
Yi Zhang, Xinyue Wei, Weichao Qiu +3
Despite the rapid growth in datasets for video activity, stable robust activity recognition with neural networks remains challenging. This is in large part due to the explosion of…
DASZL: Dynamic Action Signatures for Zero-shot Learning
Tae Soo Kim, Jonathan D. Jones, Michael Peven +6
There are many realistic applications of activity recognition where the set of potential activity descriptions is combinatorially large. This makes end-to-end supervised training o…
SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data
Qi Chen, Weichao Qiu, Yi Zhang +2
State-of-the-art techniques of artificial intelligence, in particular deep learning, are mostly data-driven. However, collecting and manually labeling a large scale dataset is both…
UnrealStereo: Controlling Hazardous Factors to Analyze Stereo Vision
Yi Zhang, Weichao Qiu, Qi Chen +2
A reliable stereo algorithm is critical for many robotics applications. But textureless and specular regions can easily cause failure by making feature matching difficult. Understa…
Maximum Margin Output Coding
Yi Zhang, Jeff Schneider
In this paper we study output coding for multi-label prediction. For a multi-label output coding to be discriminative, it is important that codewords for different label vectors ar…