no code implementations • 2 Apr 2024 • Wanrong Zheng, Haidong Zhu, Zhaoheng Zheng, Ram Nevatia
We demonstrate that with refined skeletons, the performance of the gait recognition model can achieve further improvement on public gait recognition datasets compared with state-of-the-art methods without extra annotations.
1 code implementation • 7 Dec 2023 • Zhaoheng Zheng, Jingmin Wei, Xuefeng Hu, Haidong Zhu, Ram Nevatia
Thus, we propose LLaMP, Large Language Models as Prompt learners, that produces adaptive prompts for the CLIP text encoder, establishing it as the connecting bridge.
no code implementations • 24 Oct 2023 • Haidong Zhu, Wanrong Zheng, Zhaoheng Zheng, Ram Nevatia
PSE encodes the body shape via binarized silhouettes, skeleton motions, and 3-D body shape, while AAE provides two levels of temporal appearance feature aggregation: attention-based feature aggregation and averaging aggregation.
1 code implementation • 26 May 2023 • Zhaoheng Zheng, Haidong Zhu, Ram Nevatia
In this paper, we study the problem of Compositional Zero-Shot Learning (CZSL), which is to recognize novel attribute-object combinations with pre-existing concepts.
no code implementations • 24 May 2023 • Jiongxiao Wang, Zichen Liu, Keun Hee Park, Zhuojun Jiang, Zhaoheng Zheng, Zhuofeng Wu, Muhao Chen, Chaowei Xiao
We propose a novel attack method named advICL, which aims to manipulate only the demonstration without changing the input to mislead the models.
1 code implementation • 16 Apr 2023 • Haidong Zhu, Wanrong Zheng, Zhaoheng Zheng, Ram Nevatia
Two common modalities used for representing the walking sequence of a person are silhouettes and joint skeletons.
Ranked #3 on Multiview Gait Recognition on CASIA-B
1 code implementation • 16 Apr 2023 • Haidong Zhu, Zhaoheng Zheng, Wanrong Zheng, Ram Nevatia
This paper addresses the problem of human rendering in the video with temporal appearance constancy.
no code implementations • 11 Apr 2023 • Rakesh Chada, Zhaoheng Zheng, Pradeep Natarajan
The results on downstream text-only, image-only and multimodal tasks show that our model is competitive with several strong models while using fewer parameters and lesser pre-training data.
no code implementations • 18 Dec 2022 • Haidong Zhu, Zhaoheng Zheng, Ram Nevatia
Gait recognition, which identifies individuals based on their walking patterns, is an important biometric technique since it can be observed from a distance and does not require the subject's cooperation.
no code implementations • 5 Jul 2022 • Ke Xu, Yao Xiao, Zhaoheng Zheng, Kaijie Cai, Ram Nevatia
Despite the diversity in attack patterns, adversarial patches tend to be highly textured and different in appearance from natural images.
no code implementations • CVPR 2022 • Sonam Goenka, Zhaoheng Zheng, Ayush Jaiswal, Rakesh Chada, Yue Wu, Varsha Hedau, Pradeep Natarajan
Fashion image retrieval based on a query pair of reference image and natural language feedback is a challenging task that requires models to assess fashion related information from visual and textual modalities simultaneously.
no code implementations • 25 Aug 2021 • Zhaoheng Zheng, Arka Sadhu, Ram Nevatia
We explore object detection with two attributes: color and material.
no code implementations • 1 Jan 2021 • Yizhou Zhang, Zhaoheng Zheng, Yan Liu
Recent researches have achieved substantial advances in learning structured representations from images.
no code implementations • 5 Nov 2020 • Haidong Zhu, Arka Sadhu, Zhaoheng Zheng, Ram Nevatia
The annotated language queries available during training are limited, which also limits the variations of language combinations that a model can see during training.