Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks119 from public data
- Relation-Aware Global Attention for Person Re-Identification654
This work proposes an effective Relation-Aware Global Attention (RGA) module which captures the global structural information for better attention learning and proposes to stack the relations, i.e., its pairwise correlations/affinities with all the feature positions together to learn the attention with a shallow convolutional model.
- Style Normalization and Restitution for Generalizable Person Re-Identification440
The aim of this paper is to design a generalizable person ReID framework which trains a model on source domains yet is able to generalize/perform well on target domains, and to enforce a dual causal loss constraint in SNR to encourage the separation of identity-relevant features and identity-irrelevant features.
- MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs420
A set of diagnosis tools to monitor system components and events deep in the stack, identify root causes, and derive effective techniques to achieve fault tolerance and mitigate stragglers are developed.
- Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey224
This first to present a comprehensive review of recent diffusion model-based methods on image restoration, encompassing the learning paradigm, conditional strategy, framework design, modeling strategy, and evaluation, and proposes nine potential and challenging directions for the future research of diffusion model-based IR.
- Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation218
A Nuclear-norm Wasserstein discrepancy (NWD) that has definite guidance meaning for performing discrimination is introduced that can be coupled with the classifier to serve as a discriminator satisfying the K-Lipschitz constraint without the requirements of additional weight clipping or gradient penalty strategy.
- Region Normalization for Image Inpainting207
It is shown that the mean and variance shifts caused by full-spatial FN limit the image inpainting network training and a spatial region-wise normalization named Region Normalization (RN) is proposed to overcome the limitation.
- Task Residual for Tuning Vision-Language Models182
A new efficient tuning approach for VLMs named Task Residual Tuning (TaskRes), which performs directly on the text-based classifier and explicitly decouples the prior knowledge of the pre-trained models and new knowledge regarding a target task.
- Semantics-Aligned Representation Learning for Person Re-Identification164
A framework that drives the reID network to learn semantics-aligned feature representation through delicate supervision designs is proposed and achieves the state-of-the-art performances on the benchmark datasets CUHK03, Market1501, MSMT17, and the partial person reID dataset Partial REID.
- Learning for Video Compression144
The proposed PixelMotionCNN (PMCNN) which includes motion extension and hybrid prediction networks can model spatiotemporal coherence to effectively perform predictive coding inside the learning network and provides a possible new direction to further improve compression efficiency and functionalities of future video coding.
- Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification127
This paper designs an Uncertainty-aware Multi-shot Teacher-Student (UMTS) Network that consists of a teacher network that learns the comprehensive features from multiple images of the same object, and a student network that takes a single image as input.
- Style Normalization and Restitution for Domain Generalization and Adaptation113
A novel Style Normalization and Restitution module (SNR) is designed to simultaneously ensure high generalization and discrimination capability of the networks and enforce a dual restitution loss constraint to encourage the better separation of task-relevant and task-irrelevant features.
- Is Network the Bottleneck of Distributed Training?106
A first-principles approach to measure and analyze the network performance of distributed training finds that the network is running at low utilization and that if the network can be fully utilized, distributed training can achieve a scaling factor of close to one.
- Unsupervised Single Image Deraining with Self-Supervised Constraints87
An Unsupervised Deraining Generative Adversarial Network (UD-GAN) is proposed to tackle single image deraining problems by introducing self-supervised constraints from the intrinsic statistics of unpaired rainy and clean images.
- Dense Interaction Learning for Video-based Person Re-identification77
A hybrid framework that takes the principal advantages of both CNN-based and Attention-based architectures to tackle video-based person re-ID difficulties and introduces Spatio-TEmporal Positional Embedding into the DI decoder to investigate the positional relation among the spatial-temporal inputs.
- Global Distance-Distributions Separation for Unsupervised Person Re-identification75
A global distance-distributions separation (GDS) constraint over the two distributions is introduced to encourage the clear separation of positive and negative samples from a global view and validation of the effectiveness of the GDS constraint in unsupervised ReID networks is validated.
- Learned Block-Based Hybrid Image Compression74
This paper introduces explicit intra prediction into a learned image compression framework to utilize the relation among adjacent blocks and proposes a contextual prediction module (CPM) to better capture long-range correlations by utilizing the strip pooling to extract the most relevant information in neighboring latent space, thus achieving effective information prediction.
- 73
- Particle swarm optimization using dimension selection methods69
Based on the analysis of the importance of the randomness in the PSO, another way of using randomness is proposed in PSO with random dimension selection (PSORDS) algorithm, which utilizesrandom dimension selection instead of stochastic coefficients.
- MiCS60
MiCS, which Minimizes the Communication Scale to bring down communication overhead is proposed, which can utilize heterogeneous network bandwidth, reduce network traffic over slower links, reduce the latency of communications for maintaining high network bandwidth utilization, and amortize expensive global gradient synchronization overhead.
- Multi-Prompts Learning with Cross-Modal Alignment for Attribute-based Person Re-Identification53
A new framework called Multi-Prompts ReID (MP-ReID), based on prompt learning and language models, to fully dip fine attributes to assist ReID task with off-the-shelf models for more accurate retrieval results.
- Learning Omni-Frequency Region-adaptive Representations for Real Image Super-Resolution53
This paper designs a Frequency Decomposition module to separate different frequency components to comprehensively compensate the information lost for real LR image and designs a Region-adaptive Frequency Aggregation module by leveraging dynamic convolution and spatial attention to adaptively restore frequency components for different regions.
- AI-GAN: Asynchronous interactive generative adversarial network for single image rain removal51
An Asynchronous Interactive Generative Adversarial Network (AI-GAN) is proposed to progressively disentangle the rainy image into background and rain spaces in feature level through a two-branch structure that outperforms state-of-the-art deraining methods and benefits various typical multimedia applications.
- Learning Disentangled Feature Representation for Hybrid-Distorted Image Restoration50
This work introduces the concept of Disentangled Feature Learning to achieve the feature-level divide-and-conquer of hybrid distortions and proposes the feature disentanglement module (FDM) to distribute feature representations of different distortions into different channels by revising gain-control-based normalization.
- Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models45
Binary code summarization, while invaluable for understanding code semantics, is challenging due to its labor-intensive nature, and BinSum, a comprehensive benchmark and dataset of over 557K binary functions, is presented and a new semantic similarity metric is proposed that surpasses traditional exact-match approaches.
- AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results43
This paper introduces the real image Super-Resolution challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020, and gauges the state-of-the-art approaches for real image SR in terms of PSNR and SSIM.
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.