Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks60 from public data
- 334
- Deep Learning with S-Shaped Rectified Linear Activation Units236
A novel S-shaped rectifiedlinear activation unit (SReLU) to learn both convex and non-convex functions, imitating the multiple function forms given by the two fundamental laws, namely the Webner-Fechner law and the Stevens law, in psychophysics and neural sciences is proposed.
- Deep Self-Taught Learning for Weakly Supervised Object Localization207
A deep self-taught learning approach is proposed, which makes the detector learn the object-level features reliable for acquiring tight positive samples and afterwards re-train itself based on them, which progressively improves its detection ability and localizes more informative positive samples.
- Human-Centric Spatio-Temporal Video Grounding With Visual Transformers163
This work introduces a novel task – Human-centric Spatio-Temporal Video Grounding (HC-STVG), which aims to localize a spatio-temporal tube of the target person from an untrimmed video based on a given textural description.
- Video Scene Parsing with Predictive Feature Learning117
It is experimentally proved that the learned predictive features in the model are able to significantly enhance the video parsing performance by combining with the standard image parsing network.
- HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers82
This work proposes a novel NAS method, called HR-NAS, which is able to find efficient and accurate networks for different tasks, by effectively encoding multiscale contextual information while maintaining high-resolution representations.
- 71
- Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling69
This work proposes a two-stage framework that can obtain accurate and smooth full-body motions with the three tracking signals of head and hands only and designs a set of loss terms to constrain the task of a high degree of freedom, such that it can exploit the potential of the joint-level modeling.
- 62
- Neural Architecture Search for Lightweight Non-Local Networks55
This work proposes a Lightweight Non-Local (LightNL) block by squeezing the transformation operations and incorporating compact features, and proposes an efficient neural architecture search algorithm to learn an optimal configuration of LightNL blocks in an end-to-end manner.
- 55
- Training Group Orthogonal Neural Networks with Privileged Information52
A novel group orthogonal convolutional neural network (GoCNN) that learns untangled representations within each layer by exploiting provided privileged information and enhances representation diversity effectively is proposed.
- The replenishment policy of agri-products with stochastic demand in integrated agricultural supply chains50
The results illustrated that the new replenishment policy (with intelligent method) is beneficial to help supply chain make decision scientifically, and the total cost decreases by 16.27% if the supply chains adopt the new refill policy.
- Sharing Residual Units Through Collective Tensor Factorization To Improve Deep Neural Networks47
This work revisits the standard residual function as well as its several successful variants and proposes a unified framework based on tensor Block Term Decomposition (BTD) to explain these apparently different residual functions from the tensor decomposition view.
- Video Salient Object Detection via Contrastive Features and Attention Modules44
A network with attention modules to learn contrastive features for video salient object detection without the high computational temporal modeling techniques is proposed, and a non-local self-attention scheme to capture the global information in the video frame is developed.
- 42
- 37
- 34
- 32
- 29
- 28
- 23
- 22
- 20
- 18
- 17
- CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition16
This work shows that CMAE also trivially generalizes well on video action recognition without modifying the architecture and the loss criterion, by directly replacing the original pixel shift with the temporal shift.
- 15
- 12
- 10
- 10
- Online Robust Low-Rank Tensor Learning10
This paper proposes an Online Robust Lowrank Tensor Modeling (ORLTM) approach, which dynamically explores the high-order correlations across all tensor modes for low-rank structure modeling and introduces a new dictionary learning component to analyze mixture data from multiple subspaces.
- 9
- 9
- ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding7
ScaleLong offers a fine-grained, multi-timescale benchmark for advancing MLLM capabilities in long-video understanding by embedding questions targeting four hierarchical timescales -- clip (seconds), shot (tens of seconds), event (minutes), and story (hours), all within the same video content.
- Delving Deeper into Data Scaling in Masked Image Modeling7
The study reveals that MIM can be viewed as an effective method to improve the model capacity when the scale of the training data is relatively small and MIM pre- training is data-agnostic under most scenarios, which means that the strategy of sampling pre-training data is non-critical.
- 6
- 6
- 6
- 5
- 5
- 4
- 3
- 2
- 2
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.