Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks70 from public data
- Server-Driven Video Streaming for Deep Learning Inference264
DDS (DNN-Driven Streaming), a concrete design of a video streaming protocol driven by real-time feedback from the server-side DNN, which maintains higher accuracy while reducing bandwidth usage or improves accuracy by upto 9% with no additional bandwidth usage.
- Multimodal Contrastive Training for Visual Representation Learning229
This work develops an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives, and exploits intrinsic data properties within each modality and semantic information from cross- modal correlation simultaneously, hence improving the quality of learned visual representations.
- 166
- AM-LFS: AutoML for Loss Function Search77
This paper proposes AutoML for Loss Function Search (AM-LFS) which leverages REINFORCE to search loss functions during the training process and proposes an efficient optimization framework which can dynamically optimize the parameters of loss function's distribution during training.
- 55
- Multi-Prototype Networks for Unconstrained Set-based Face Recognition52
A novel Multi-Prototype Network (MPNet) model is proposed to learn multiple prototype face representations adaptively from the media sets to demonstrate superiority of the proposed model over state-of-the-arts.
- Classification of in vivo autofluorescence spectra using support vector machines52
An algorithm based on support vector machines (SVM), the most recent advance in pattern recognition, is presented for use in classifying light-induced autofluorescence collected from cancerous and normal tissues and a method combining PCA and SVM techniques for reducing the complexity is investigated.
- ECG signal denoising based on deep factor analysis44
The noise reduction of the network is improved through a supervised fine-tuning of the parameters of the proposed deep network model, thus increasing the robustness of the whole system in clinical applications and preserving useful information while removing noises from the ECG signal.
- Relaxation-Free Deep Hashing via Policy Gradient42
This approach formulates the non-smooth part of the hashing network as sampling with a stochastic policy, so that the retrieval performance degradation caused by the relaxation can be avoided and the differentiation challenge for discrete optimization can be naturally addressed.
- Rank-in-Rank Loss for Person Re-identification38
Extensive experimental results indicate that the proposed Differentiable Retrieval-Sort Loss (DRSL) can improve the performance of the state-of-the-art re-ID models, thus demonstrating its effectiveness and superiority in the re- ID task.
- 31
- Image Super-Resolution with Text Prompt Diffusion28
This work proposes the PromptSR, a text-image generation pipeline to integrate text into the SR dataset through the text degradation representation and degradation model, which leverages the latest multi-modal large language model (MLLM) to generate prompts from low-resolution images.
- VAGeo: View-specific Attention for Cross-View Object Geo-Localization18
A novel View-specific Attention Geo-localization method (VAGeo) for accurate CVOGL, which contains two key modules: view-specific positional encoding (VSPE) module and channel-spatial hybrid attention (CSHA) module.
- 15
- Inflation with Diffusion: Efficient Temporal Adaptation for Text-to-Video Super-Resolution14
An efficient diffusion-based text-to-video super-resolution (SR) tuning approach that leverages the readily learned capacity of pixel level image diffusion model to capture spatial information for video generation by inflating the weightings of the text-to-image SR model into the video generation framework is proposed.
- Mix-Modality Person Re-Identification: A New and Practical Paradigm13
A Mix-Modality Person Re-Identification (MM-ReID) task is proposed, the influence of modality mixing ratio on performance is explored, and mix-modality test sets for existing datasets are constructed according to the new mix-modality testing paradigm.
- 13
- 11
- Spatial-Frequency U-Net for Denoising Diffusion Probabilistic Models11
This paper designs a novel architecture SFUNet to effectively capture the correlation for both spatial and frequency domains in wavelet data and finds the model is able to generate images with higher quality on CIFAR-10, FFHQ, LSUN-Bedroom, and LSun-Church datasets, than the pixel-based counterpart.
- QR Code Detection with Faster-RCNN Based on FPN10
This work adds an FPN module to the Faster-RCNN to improve the detection performance for small and multi-scale QR code, and shows that the method has achieved good performances in the detection of QR code in complex scenes.
- 10
- 9
- Identity Hides in Darkness: Learning Feature Discovery Transformer for Nighttime Person Re-Identification8
A novel nighttime person Re-ID method, termed Feature Discovery Transformer (FDT), explicitly capturing the pedestrian identity information hidden in darkness at night, which can achieve state-of-the-art performance on two realistic nighttime person Re-ID benchmarks, i.e., Night600 and RGBNT201rgb datasets.
- Machine Learning Models Based on UAV Oblique Images Improved Above‐Ground Biomass Estimation Accuracy Across Diverse Grasslands on the Qinghai–Tibetan Plateau8
Comparative results on estimations of different grassland types indicated that oblique images helped reduce the models' root mean square error (RMSE), particularly in the machine learning models.
- Blind 3D Video Stabilization with Spatio-Temporally Varying Motion Blur8
The Cross-frame-temporal Module framework is proposed to address blind motion blur induced by various conditions, which utilizes cross-frame temporal features to estimate depth maps and camera motion and outperforms state-of-the-art methods.
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 2026-10-15. 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.