no code implementations • NeurIPS 2023 • Xinyu Zhou, Pinxue Guo, Lingyi Hong, Jinglun Li, Wei zhang, Weifeng Ge, Wenqiang Zhang
Therefore, using all features in the template and memory can lead to redundancy and impair tracking performance.
no code implementations • 19 Jan 2024 • Haibo Wang, Chenghang Lai, Yixuan Sun, Weifeng Ge
GCG learns multiple Gaussian functions to characterize the temporal structure of the video, and sample question-critical frames as positive moments to be the visual inputs of LMMs.
no code implementations • 19 Jan 2024 • Haibi Wang, Weifeng Ge
With the breakthrough of multi-modal large language models, answering complex visual questions that demand advanced reasoning abilities and world knowledge has become a much more important testbed for developing AI models than ever.
1 code implementation • 24 May 2023 • Hua Cai, Xuli Shen, Qing Xu, Weilin Shen, Xiaomei Wang, Weifeng Ge, Xiaoqing Zheng, xiangyang xue
To this end, we propose a novel approach for empathetic response generation, which incorporates an adaptive module for commonsense knowledge selection to ensure consistency between the generated empathetic responses and the speaker's situation.
no code implementations • ICCV 2023 • Jinglun Li, Xinyu Zhou, Pinxue Guo, Yixuan Sun, Yiwen Huang, Weifeng Ge, Wenqiang Zhang
We use one fold as the in-distribution dataset and the others as out-of-distribution datasets to evaluate the proposed method.
1 code implementation • ICCV 2023 • Yiwen Huang, Yixuan Sun, Chenghang Lai, Qing Xu, Xiaomei Wang, Xuli Shen, Weifeng Ge
Following the spirit of multiple instance learning (MIL), we decompose the weakly supervised correspondence learning problem into three stages: image-level matching, region-level matching, and pixel-level matching.
1 code implementation • CVPR 2023 • Yixuan Sun, Dongyang Zhao, Zhangyue Yin, Yiwen Huang, Tao Gui, Wenqiang Zhang, Weifeng Ge
The asymmetric feature learning module exploits a biased cross-attention mechanism to encode token features of source images with their target counterparts.
1 code implementation • CVPR 2023 • Yixuan Sun, Yiwen Huang, Haijing Guo, Yuzhou Zhao, Runmin Wu, Yizhou Yu, Weifeng Ge, Wenqiang Zhang
Semantic correspondence have built up a new way for object recognition.
no code implementations • 19 Dec 2022 • Xiaowen Qiu, Ruize Xu, Boan He, Yingtao Zhang, Wenqiang Zhang, Weifeng Ge
The style removal network removes the original image styles, and the style restoration network recovers image styles in a supervised manner.
1 code implementation • 28 Nov 2022 • Qianyu Guo, Hongtong Gong, Xujun Wei, Yanwei Fu, Weifeng Ge, Yizhou Yu, Wenqiang Zhang
This paper introduces a new few-shot learning pipeline that casts relevance ranking for image retrieval as binary ranking relation classification.
no code implementations • MM '22: Proceedings of the 30th ACM International Conference on Multimedia 2022 • Yan Wang, Yixuan Sun, Wei Song, Shuyong Gao, Yiwen Huang, Zhaoyu Chen, Weifeng Ge, and Wenqiang Zhang
To obtain consistent prediction probabilities from the dual path, we further propose a dual path regularization loss, aiming to minimize the divergence between the distributions of two-path embeddings.
Ranked #13 on Dynamic Facial Expression Recognition on DFEW
Dynamic Facial Expression Recognition Representation Learning
1 code implementation • CVPR 2022 • Yangji He, Weihan Liang, Dongyang Zhao, Hong-Yu Zhou, Weifeng Ge, Yizhou Yu, Wenqiang Zhang
To improve data efficiency, we propose hierarchically cascaded transformers that exploit intrinsic image structures through spectral tokens pooling and optimize the learnable parameters through latent attribute surrogates.
Ranked #1 on Few-Shot Learning on Mini-ImageNet - 1-Shot Learning
no code implementations • CVPR 2022 • Yan Wang, Yixuan Sun, Yiwen Huang, Zhongying Liu, Shuyong Gao, Wei zhang, Weifeng Ge, Wenqiang Zhang
Current benchmarks for facial expression recognition (FER) mainly focus on static images, while there are limited datasets for FER in videos.
2 code implementations • ICCV 2021 • Gangming Zhao, Weifeng Ge, Yizhou Yu
State-of-the-art methods for multi-scale feature learning focus on performing feature interactions across space and scales using neural networks with a fixed topology.
1 code implementation • ICCV 2021 • Dongyang Zhao, Ziyang Song, Zhenghao Ji, Gangming Zhao, Weifeng Ge, Yizhou Yu
We follow the coarse-to-fine matching strategy and build a top-down feature and matching enhancement scheme that is coupled with the multi-scale hierarchy of deep convolutional neural networks.
Ranked #11 on Semantic correspondence on SPair-71k
no code implementations • ICCV 2019 • Weifeng Ge, Sheng Guo, Weilin Huang, Matthew R. Scott
Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only.
Ranked #9 on Image-level Supervised Instance Segmentation on PASCAL VOC 2012 val (using extra training data)
General Classification Image-level Supervised Instance Segmentation +6
1 code implementation • CVPR 2019 • Weifeng Ge, Xiangru Lin, Yizhou Yu
We build complementary parts models in a weakly supervised manner to retrieve information suppressed by dominant object parts detected by convolutional neural networks.
Ranked #22 on Fine-Grained Image Classification on CUB-200-2011
no code implementations • ECCV 2018 • Weifeng Ge, Weilin Huang, Dengke Dong, Matthew R. Scott
(i) we construct a hierarchical class-level tree where neighboring classes are merged recursively.
Ranked #8 on Image Retrieval on CARS196
1 code implementation • 18 Sep 2018 • Weifeng Ge, Bingchen Gong, Yizhou Yu
With respect to a downsampled low resolution image, we model a high resolution image as a combination of two components, a deterministic component and a stochastic component.
no code implementations • CVPR 2018 • Weifeng Ge, Sibei Yang, Yizhou Yu
In this paper, we propose a novel weakly supervised curriculum learning pipeline for multi-label object recognition, detection and semantic segmentation.
Ranked #15 on Weakly Supervised Object Detection on PASCAL VOC 2007
1 code implementation • CVPR 2017 • Weifeng Ge, Yizhou Yu
In this paper, we introduce a source-target selective joint fine-tuning scheme for improving the performance of deep learning tasks with insufficient training data.