no code implementations • 29 Nov 2024 • Wenbo Zhang, Lu Zhang, Ping Hu, Liqian Ma, Yunzhi Zhuge, Huchuan Lu
Injecting semantics into 3D Gaussian Splatting (3DGS) has recently garnered significant attention.
1 code implementation • 26 Nov 2024 • Yicheng Yang, Pengxiang Li, Lu Zhang, Liqian Ma, Ping Hu, Siyu Du, Yunzhi Zhuge, Xu Jia, Huchuan Lu
Extensive experiments demonstrate that DreamMix effectively balances identity preservation and attribute editability across various application scenarios, including object insertion, attribute editing, and small object inpainting.
no code implementations • 7 Oct 2024 • Xiaorui Sun, Jun Liu, Heng Tao Shen, Xiaofeng Zhu, Ping Hu
The Segment Anything Model (SAM) is a foundational model for image segmentation tasks, known for its strong generalization across diverse applications.
1 code implementation • IJCAI 2024 • Jincheng Huang, Yujie Mo, Ping Hu, Xiaoshuang Shi, Shangbo Yuan, Zeyu Zhang, Xiaofeng Zhu
Manymethods of Directed Graph Neural Networks (DGNNs) are designed to equally treat nodes in the same neighbor set (i. e., out-neighbor set and in-neighbor set) for every node, without consider ing the node diversity in directed graphs, so they are often unavailable to adaptively acquire suitable information from neighbors of different directions.
no code implementations • 27 Apr 2024 • Yujing Liu, Zongqian Wu, Zhengyu Lu, Ci Nie, Guoqiu Wen, Ping Hu, Xiaofeng Zhu
Furthermore, we design a new bi-level optimization strategy to dynamically adjust the teacher weight matrix based on the training progress of the student model.
no code implementations • CVPR 2024 • Reuben Tan, Ximeng Sun, Ping Hu, Jui-Hsien Wang, Hanieh Deilamsalehy, Bryan A. Plummer, Bryan Russell, Kate Saenko
Long video question answering is a challenging task that involves recognizing short-term activities and reasoning about their fine-grained relationships.
2 code implementations • CVPR 2024 • Jiazuo Yu, Yunzhi Zhuge, Lu Zhang, Ping Hu, Dong Wang, Huchuan Lu, You He
Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset.
no code implementations • 11 Mar 2024 • Leo Chen, Benjamin Boardley, Ping Hu, Yiru Wang, Yifan Pu, Xin Jin, Yongqiang Yao, Ruihao Gong, Bo Li, Gao Huang, Xianglong Liu, Zifu Wan, Xinwang Chen, Ning Liu, Ziyi Zhang, Dongping Liu, Ruijie Shan, Zhengping Che, Fachao Zhang, Xiaofeng Mou, Jian Tang, Maxim Chuprov, Ivan Malofeev, Alexander Goncharenko, Andrey Shcherbin, Arseny Yanchenko, Sergey Alyamkin, Xiao Hu, George K. Thiruvathukal, Yung Hsiang Lu
This article describes the 2023 IEEE Low-Power Computer Vision Challenge (LPCVC).
no code implementations • 18 Jan 2024 • Lars Ericson, Xuejun Zhu, Xusi Han, Rao Fu, Shuang Li, Steve Guo, Ping Hu
The objectives for financial time series generation are to generate synthetic data paths with good variety, and similar distribution and dynamics to the original historical data.
no code implementations • 30 Nov 2023 • Zongqian Wu, Yujing Liu, Mengmeng Zhan, Jialie Shen, Ping Hu, Xiaofeng Zhu
Although current prompt learning methods have successfully been designed to effectively reuse the large pre-trained models without fine-tuning their large number of parameters, they still have limitations to be addressed, i. e., without considering the adverse impact of meaningless patches in every image and without simultaneously considering in-sample generalization and out-of-sample generalization.
no code implementations • 29 Oct 2023 • Ping Hu, Simon Niklaus, Lu Zhang, Stan Sclaroff, Kate Saenko
In this work, we first propose a fully differentiable Many-to-Many (M2M) splatting framework to interpolate frames efficiently.
no code implementations • ICCV 2023 • Duo Peng, Ping Hu, Qiuhong Ke, Jun Liu
Translating images from a source domain to a target domain for learning target models is one of the most common strategies in domain adaptive semantic segmentation (DASS).
no code implementations • 3 Aug 2023 • Ping Hu, Ximeng Sun, Stan Sclaroff, Kate Saenko
Previous works have focused on learning the alignment between textual and visual spaces to compensate for limited image labels, yet may suffer from reduced accuracy due to the scarcity of high-quality multi-label annotations.
no code implementations • 15 Jun 2023 • Ping Hu, Virginia Bordignon, Mert Kayaalp, Ali H. Sayed
This paper studies the probability of error associated with the social machine learning framework, which involves an independent training phase followed by a cooperative decision-making phase over a graph.
no code implementations • CVPR 2023 • Tianjiao Li, Lin Geng Foo, Ping Hu, Xindi Shang, Hossein Rahmani, Zehuan Yuan, Jun Liu
Pre-training VTs on such corrupted data can be challenging, especially when we pre-train via the masked autoencoding approach, where both the inputs and masked ``ground truth" targets can potentially be unreliable in this case.
no code implementations • ICCV 2023 • Desai Xie, Ping Hu, Xin Sun, Soren Pirk, Jianming Zhang, Radomir Mech, Arie E. Kaufman
Placing and orienting a camera to compose aesthetically meaningful shots of a scene is not only a key objective in real-world photography and cinematography but also for virtual content creation.
1 code implementation • 20 Jun 2022 • Ximeng Sun, Ping Hu, Kate Saenko
Solving multi-label recognition (MLR) for images in the low-label regime is a challenging task with many real-world applications.
1 code implementation • CVPR 2022 • Ping Hu, Simon Niklaus, Stan Sclaroff, Kate Saenko
Motion-based video frame interpolation commonly relies on optical flow to warp pixels from the inputs to the desired interpolation instant.
Ranked #1 on
Video Frame Interpolation
on Xiph-4K (Crop)
no code implementations • 14 Mar 2022 • Ping Hu, Virginia Bordignon, Stefan Vlaski, Ali H. Sayed
Adaptive social learning is a useful tool for studying distributed decision-making problems over graphs.
no code implementations • 25 Jan 2022 • Simon Niklaus, Ping Hu, Jiawen Chen
Frame interpolation is an essential video processing technique that adjusts the temporal resolution of an image sequence.
no code implementations • 3 Dec 2021 • Kuniaki Saito, Ping Hu, Trevor Darrell, Kate Saenko
LDET leads to significant improvements on many datasets in the open-world instance segmentation task, outperforming baselines on cross-category generalization on COCO, as well as cross-dataset evaluation on UVO and Cityscapes.
no code implementations • 11 Jun 2021 • Feihong Shen, Jun Liu, Ping Hu
In this work, we consider counterfactual methods to avoid the confounder in the original model.
1 code implementation • CVPR 2022 • Dina Bashkirova, Mohamed Abdelfattah, Ziliang Zhu, James Akl, Fadi Alladkani, Ping Hu, Vitaly Ablavsky, Berk Calli, Sarah Adel Bargal, Kate Saenko
Recyclable waste detection poses a unique computer vision challenge as it requires detection of highly deformable and often translucent objects in cluttered scenes without the kind of context information usually present in human-centric datasets.
no code implementations • NeurIPS 2020 • Ping Hu, Stan Sclaroff, Kate Saenko
Recently, most ZSS methods focus on learning the visual-semantic correspondence to transfer knowledge from seen classes to unseen classes at the pixel level.
1 code implementation • 7 Jul 2020 • Ping Hu, Federico Perazzi, Fabian Caba Heilbron, Oliver Wang, Zhe Lin, Kate Saenko, Stan Sclaroff
The proposed architecture relies on our fast spatial attention, which is a simple yet efficient modification of the popular self-attention mechanism and captures the same rich spatial context at a small fraction of the computational cost, by changing the order of operations.
Ranked #32 on
Semantic Segmentation
on DensePASS
1 code implementation • CVPR 2020 • Ping Hu, Fabian Caba Heilbron, Oliver Wang, Zhe Lin, Stan Sclaroff, Federico Perazzi
We present TDNet, a temporally distributed network designed for fast and accurate video semantic segmentation.
Ranked #2 on
Video Semantic Segmentation
on Cityscapes val
no code implementations • 11 Jun 2019 • Ping Hu, Ximeng Sun, Kate Saenko, Stan Sclaroff
Learning from a few examples is a challenging task for machine learning.
no code implementations • CVPR 2018 • Ping Hu, Gang Wang, Xiangfei Kong, Jason Kuen, Yap-Peng Tan
Then, the proposed Cascaded Refinement Network(CRN) takes the coarse segmentation as guidance to generate an accurate segmentation of full resolution.
no code implementations • CVPR 2017 • Ping Hu, Bing Shuai, Jun Liu, Gang Wang
Our method drives the network to learn a Level Set function for salient objects so it can output more accurate boundaries and compact saliency.
no code implementations • CVPR 2017 • Jun Liu, Gang Wang, Ping Hu, Ling-Yu Duan, Alex C. Kot
Hence we propose a new class of LSTM network, Global Context-Aware Attention LSTM (GCA-LSTM), for 3D action recognition, which is able to selectively focus on the informative joints in the action sequence with the assistance of global contextual information.
Ranked #7 on
One-Shot 3D Action Recognition
on NTU RGB+D 120
no code implementations • 9 Jun 2016 • Jan Hladky, Ping Hu, Diana Piguet
We introduce a counterpart to the notion of vertex disjoint tilings by copy of a fixed graph F to the setting of graphons.
Combinatorics