Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Tae‐Kyun KimSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works139 from public data
- Multiple object tracking: A literature review1,098
This work provides a thorough review on the development of this problem in recent decades and inspects the recent advances in various aspects and proposes some interesting directions for future research.
- Bi-Real Net: Enhancing the Performance of 1-Bit CNNs with Improved Representational Capability and Advanced Training Algorithm662
A novel model, dubbed Bi-Real net, which connects the real activations (after the 1-bit convolution and/or BatchNorm layer, before the sign function) to activations of the consecutive block, through an identity shortcut is proposed, which achieves up to 10% higher top-1 accuracy with more memory saving and lower computational cost.
- Learning to Compose Dynamic Tree Structures for Visual Contexts623
A hybrid learning procedure is developed which integrates end-task supervised learning and the tree structure reinforcement learning, where the former's evaluation result serves as a self-critic for the latter's structure exploration.
- 543
- Deblurring by Realistic Blurring494
This paper proposes a new method which combines two GAN models, i.e., a learning-to-Blur GAN (BGAN) and learning- to-DeBlurGAN (DBGAN), in order to learn a better model for image deblurring by primarily learning how to blur images.
- Deep Image Deblurring: A Survey415
This paper presents a comprehensive and timely survey of recently published deep-learning based image deblurring approaches, aiming to serve the community as a useful literature review.
- Deep Dense Multi-Scale Network for Snow Removal Using Semantic and Depth Priors370
This paper proposes a Deep Dense Multi-Scale Network for snow removal by exploiting semantic and geometric priors, and designs a DDMSNet to learn semantic-aware and geometry-aware representation via a self-attention mechanism to produce the final clean images.
- Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis292
A 3D body mesh recovery module is proposed to disentangle the pose and shape, which can not only model the joint location and rotation but also characterize the personalized body shape and is able to support a more flexible warping from multiple sources.
- MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing291
A new Transformer variant, named Multi-branch Transformer expanded by Taylor formula (MB-TaylorFormer), which can em-bed coarse to fine features more flexibly at the patch embedding stage and capture long-distance pixel interactions with limited computational cost.
- MB-TaylorFormer V2: Improved Multi-Branch Linear Transformer Expanded by Taylor Formula for Image Restoration277
The proposed model, named the second version of Taylor formula expansion-based Transformer (for short MB-TaylorFormer V2) has the capability to concurrently process coarse-to-fine features, capture long-distance pixel interactions with limited computational cost, and improve the approximation of the Taylor expansion remainder.
- GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions240
The GridFormer framework achieves state-of-the-art results on five diverse image restoration tasks in adverse weather conditions, including image deraining, dehazing, deraining & dehazing, desnowing, and multi-weather restoration.
- 239
- 236
- Enhanced Spatio-Temporal Interaction Learning for Video Deraining: Faster and Better220
A new end-to-end video deraining framework, dubbed Enhanced Spatio-Temporal Interaction Network (ESTINet), which considerably boosts current state-of-the-art video derained quality and speed and takes the advantage of deep residual networks and convolutional long short-term memory.
- Learning to Generate Time-Lapse Videos Using Multi-stage Dynamic Generative Adversarial Networks207
This work presents a generative adversarial network (GAN) based two-stage approach to generating realistic time-lapse videos of high resolution and demonstrates the superiority of this model over the state-of-the-art models.
- MC-Blur: A Comprehensive Benchmark for Image Deblurring188
This paper constructs a new large-scale multi-cause image deblurring dataset (MC-Blur), including real-world and synthesized blurry images with different blur factors, and conducts extensive benchmarking studies to compare SOTA methods in different scenarios, analyze their efficiency, and investigate the buildataset’s capacity.
- Uni-MoE: Scaling Unified Multimodal LLMs With Mixture of Experts180
This work presents the pioneering attempt to develop a unified MLLM with the MoE architecture, named Uni-MoE that can handle a wide array of modalities and implements a sparse MoE architecture within the LLMs to enable efficient training and inference through modality-level data parallelism and expert-level model parallelism.
- End-to-End Active Object Tracking and Its Real-World Deployment via Reinforcement Learning160
The tracker trained in simulators (ViZDoom and Unreal Engine) demonstrates good generalization behaviors in the case of unseen object moving paths, unseen object appearances, unseen backgrounds, and distracting objects and can restore tracking after occasional lost of the target being tracked.
- 155
- 153
- 143
- 133
- Few-shot Object Counting with Similarity-Aware Feature Enhancement127
This work studies the problem of few-shot object counting, which counts the number of exemplar objects occurring in the query image, and proposes a novel learning block, equipped with a similarity comparison module and a feature enhancement module, which surpass the state-of-the-art methods by a sufficiently large margin.
- Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video118
This paper localizes a spatio-temporal tube in the video that semantically corresponds to the given sentence, with no reliance on any spatio/temporal annotations during training, and proposes a new attentive interactor to strengthen the matching behaviors of reliable instance-sentence pairs and penalize the unreliable ones.
- Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance115
Bi-Real net with a novel training algorithm is proposed with a tighter approximation to the derivative of the sign function, a magnitude-aware binarization for weight updating, a better initialization method, and a two-step scheme for training a deep network.
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.