no code implementations • 7 Apr 2024 • YiFan Li, Anh Dao, Wentao Bao, Zhen Tan, Tianlong Chen, Huan Liu, Yu Kong
Our initiative on the dataset and benchmarks reveal the nature and rationale of facial affective behaviors, i. e., fine-grained facial movement, interpretability, and reasoning.
1 code implementation • 20 Feb 2024 • Zhen Tan, Chengshuai Zhao, Raha Moraffah, YiFan Li, Yu Kong, Tianlong Chen, Huan Liu
Unlike direct harmful output generation for MLLMs, our research demonstrates how a single MLLM agent can be subtly influenced to generate prompts that, in turn, induce other MLLM agents in the society to output malicious content.
no code implementations • 20 Nov 2023 • YiFan Li, Zhen Tan, Kai Shu, Zongsheng Cao, Yu Kong, Huan Liu
Graph Neural Networks (GNNs) have emerged as a powerful tool for representation learning on graphs, but they often suffer from overfitting and label noise issues, especially when the data is scarce or imbalanced.
no code implementations • 19 Sep 2023 • Wentao Bao, Qi Yu, Yu Kong
A recent trend in OSR shows the benefit of generative models to discriminative unknown detection.
no code implementations • 18 Sep 2023 • Xinmiao Lin, Wentao Bao, Qi Yu, Yu Kong
Neural pathways as model explanations consist of a sparse set of neurons that provide the same level of prediction performance as the whole model.
no code implementations • 5 Sep 2023 • Junwen Chen, Jie Zhu, Yu Kong
Despite significant progress in video question answering (VideoQA), existing methods fall short of questions that require causal/temporal reasoning across frames.
Ranked #17 on Video Question Answering on NExT-QA
1 code implementation • ICCV 2023 • Wentao Bao, Lele Chen, Libing Zeng, Zhong Li, Yi Xu, Junsong Yuan, Yu Kong
In this paper, we set up an egocentric 3D hand trajectory forecasting task that aims to predict hand trajectories in a 3D space from early observed RGB videos in a first-person view.
no code implementations • 23 May 2023 • Wentao Bao, Lichang Chen, Heng Huang, Yu Kong
Orthogonal to the existing literature of soft, hard, or distributional prompts, our method advocates prompting the LLM-supported class distribution that leads to a better zero-shot generalization.
1 code implementation • CVPR 2023 • Xinmiao Lin, Yikang Li, Jenhao Hsiao, Chiuman Ho, Yu Kong
The popular VQ-VAE models reconstruct images through learning a discrete codebook but suffer from a significant issue in the rapid quality degradation of image reconstruction as the compression rate rises.
no code implementations • CVPR 2022 • Junwen Chen, Gaurav Mittal, Ye Yu, Yu Kong, Mei Chen
We present GateHUB, Gated History Unit with Background Suppression, that comprises a novel position-guided gated cross-attention mechanism to enhance or suppress parts of the history as per how informative they are for current frame prediction.
Ranked #1 on Online Action Detection on TVSeries
no code implementations • 3 Apr 2022 • Krishna Prasad Neupane, Ervine Zheng, Yu Kong, Qi Yu
We present a novel dynamic recommendation model that focuses on users who have interactions in the past but turn relatively inactive recently.
no code implementations • CVPR 2022 • Shuai Li, Yu Kong, Hamid Rezatofighi
This paper concerns the problem of multi-object tracking based on the min-cost flow (MCF) formulation, which is conventionally studied as an instance of linear program.
1 code implementation • CVPR 2022 • Wentao Bao, Qi Yu, Yu Kong
The OpenTAL is general to enable existing TAL models for open set scenarios, and experimental results on THUMOS14 and ActivityNet1. 3 benchmarks show the effectiveness of our method.
no code implementations • 2 Feb 2022 • Hanbin Hong, Yuan Hong, Yu Kong
In this paper, we show that the gradients can also be exploited as a powerful weapon to defend against adversarial attacks.
no code implementations • 1 Nov 2021 • Xinmiao Lin, Wentao Bao, Matthew Wright, Yu Kong
In many applications, it is essential to understand why a machine learning model makes the decisions it does, but this is inhibited by the black-box nature of state-of-the-art neural networks.
1 code implementation • ICCV 2021 • Wentao Bao, Qi Yu, Yu Kong
Traffic accident anticipation aims to accurately and promptly predict the occurrence of a future accident from dashcam videos, which is vital for a safety-guaranteed self-driving system.
2 code implementations • ICCV 2021 • Wentao Bao, Qi Yu, Yu Kong
Different from image data, video actions are more challenging to be recognized in an open-set setting due to the uncertain temporal dynamics and static bias of human actions.
no code implementations • ICCV 2021 • Junwen Chen, Yu Kong
Video entailment aims at determining if a hypothesis textual statement is entailed or contradicted by a premise video.
1 code implementation • ECCV 2020 • Junwen Chen, Wentao Bao, Yu Kong
Our model explicitly anticipates both activity features and positions by two graph auto-encoders, aiming to learn a discriminative group representation for group activity prediction.
2 code implementations • 1 Aug 2020 • Wentao Bao, Qi Yu, Yu Kong
The derived uncertainty-based ranking loss is found to significantly boost model performance by improving the quality of relational features.
Ranked #2 on Accident Anticipation on CCD
no code implementations • 20 Jul 2020 • Wentao Bao, Qi Yu, Yu Kong
Monocular 3D object detection aims to detect objects in a 3D physical world from a single camera.
no code implementations • 25 Nov 2019 • Zhichao Fu, Yu Kong, Yingbin Zheng, Hao Ye, Wenxin Hu, Jing Yang, Liang He
The accuracy of OCR is usually affected by the quality of the input document image and different kinds of marred document images hamper the OCR results.
3 code implementations • 25 Dec 2018 • Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, Yun Fu
We fully exploit the hierarchical features from all the convolutional layers.
no code implementations • 28 Jun 2018 • Yu Kong, Yun Fu
Derived from rapid advances in computer vision and machine learning, video analysis tasks have been moving from inferring the present state to predicting the future state.
16 code implementations • CVPR 2018 • Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, Yun Fu
In this paper, we propose a novel residual dense network (RDN) to address this problem in image SR. We fully exploit the hierarchical features from all the convolutional layers.
Ranked #3 on Color Image Denoising on CBSD68 sigma50
no code implementations • CVPR 2017 • Yu Kong, Zhiqiang Tao, Yun Fu
Different from after-the-fact action recognition, action prediction task requires action labels to be predicted from these partially observed videos.
no code implementations • CVPR 2015 • Yu Kong, Yun Fu
Rich heterogeneous RGB and depth data are effectively compressed and projected to a learned shared space, in order to reduce noise and capture useful information for recognition.