Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks24 from public data
- DepGraph: Towards Any Structural Pruning566
This work proposes a general and fully automatic method, Dependency Graph (DepGraph), to explicitly model the dependency between layers and comprehensively group coupled parameters for pruning, and demonstrates that, even with a simple norm-based criterion, the proposed method consistently yields gratifying performances.
- TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration127
The approach can generate realistic and coherent dance movements conditioned on both text and music while maintaining comparable performance with the two single modalities, and two novel metrics are introduced to measure the coherence and freezing percentage of the generated motion.
- Priority-Centric Human Motion Generation in Discrete Latent Space93
A Priority-Centric Motion Discrete Diffusion Model (M2DM) is introduced, which utilizes a Transformer-based VQ-VAE to derive a concise, discrete motion representation, incorporating a global self-attention mechanism and a regularization term to counteract code collapse.
- Improving Deep Regression with Ordinal Entropy72
This work provides a derivation to show that classification, with the cross-entropy loss, outperforms regression with a mean squared error loss in its ability to learn high-ent entropy feature representations.
- Enhancing Video Super-Resolution via Implicit Resampling-based Alignment62
Experiments on synthetic and real-world datasets show that alignment with the proposed implicit resampling enhances the performance of state-of-the-art frameworks with minimal impact on both compute and parameters.
- PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision47
This paper proposes a novel self-supervised approach that allows us to explicitly generate 2D-3D pose pairs for augmenting supervision, through a self-enhancing dual-loop learning framework, and achieves encouraging results significantly outperforming the state of the art and, in some cases, even on par with results of fully-super supervised methods.
- Bias-Compensated Integral Regression for Human Pose Estimation29
This paper uncovers an induced bias from integral regression that results from combining the softmax and the expectation operation, and proposes Bias Compensated Integral Regression (BCIR), an integral regression-based framework that compensates for the bias.
- Point2Seq: Detecting 3D Objects as Sequences28
Without bells and whistles, the Point2Seq framework significantly out-performs previous anchor- and center-based 3D object detection frameworks, yielding the new state of the art on the challenging ONCE dataset as well as the Waymo Open Dataset.
- Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention20
This work proposes a semantic segmentation method for multiple adverse weather conditions that incorporates adaptive knowledge acquisition, pseudo-label blending, and weather composition replay and obtains the best performance with averaged mIoU (%) of 65.7 and the lowest forgetting (%).
- 19
- Overcoming the TradeOff between Accuracy and Plausibility in 3D Hand Shape Reconstruction11
This work introduces a novel weakly-supervised hand shape estimation framework that integrates non-parametric mesh fitting with MANO model in an end-to-end fashion to yield well-aligned and high-quality 3D meshes, especially in challenging two-hand and hand-object interaction scenarios.
- 10
- Unraveling Motion Uncertainty for Local Motion Deblurring8
This work proposes a novel method named Motion-Uncertainty-Guided Network (MUGNet), which harnesses a probabilistic representational model to explicitly address the intricacies stemming from motion uncertainties and demonstrates the superiority of the MUGNet with extensive experiments.
- MetaISP: Efficient RAW-to-sRGB Mappings with Merely 1M Parameters7
The proposed MetaISP is a streamlined model that achieves superior reconstruction quality by adaptively modulating its parameters and architecture in response to diverse inputs by predicting dynamic weights for each input image and combining these weights with multiple learnable basis matrices to construct the correction matrices.
- 6
- End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning6
The novelty of the approach is introduced: the first end-to-end, optical-flow-free, domain-adaptive video semantic segmentation method, enforcing the model to actively exploit the temporal information from adjacent frames through a fusion block and temporal-spatial teachers.
- Semantic Segmentation on Raindrop Degraded Images Using Two-Stage Dual Teacher-Student Learning5
This work tackles the complex problem of raindrop degradation by dividing it into two distinct challenges: degraded visual appearance and raindrop occlusion, and employs a collaborative approach to decompose and address raindrop-induced degradations.
- Vista3D: Unravel the 3D Darkside of a Single Image3
Vista3D is presented, a framework that realizes swift and consistent 3D generation within a mere 5 minutes and elevates the quality of generation by using a disentangled representation with two independent implicit functions to capture both visible and obscured aspects of objects.
- 3
- Learning Unorthogonalized Matrices for Rotation Estimation3
By replacing the orthogonalization incorporated representation with the proposed PRoM in various rotation-related tasks, this work achieves state-of-the-art results on large-scale benchmarks for human pose estimation.
- 1
- GhostRNN: Reducing State Redundancy in RNN with Cheap Operations1
An efficient RNN architecture, GhostRNN, which reduces hidden state redundancy with cheap operations, and observes that partial dimensions of hidden states are similar to the others in trained RNN models, suggesting that redundancy exists in specific RNNs.
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. 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.