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.
- 112
- 110
- Multiple Object Tracking: A Review.108
A comprehensive and systematic review of the recent advances in various aspects about multiple object tracking and provides some potential directions with insights for MOT, which are still open issues and need more research efforts.
- PRIOR: Prototype Representation Joint Learning from Medical Images and Reports106
Experimental results on five downstream tasks, including supervised classification, zero-shot classification, image-to-text retrieval, semantic segmentation, and object detection, show the proposed method outperforms other state-of-the-art methods across multiple datasets and under different dataset size settings.
- 80
- 80
- Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior78
A Paired Rain Removal Network (PRRNet), which exploits both stereo images and semantic information is presented, and a Semantic-Aware Deraining Module (SADM) is developed which solves both tasks of semantic segmentation and deraining of scenes.
- 70
- Context-Aware Integration of Language and Visual References for Natural Language Tracking69
A joint multi-modal tracking framework with a prompt modulation module to leverage the complementarity between temporal visual templates and language expressions, enabling precise and context-aware appearance and linguistic cues, and a unified target decoding module to integrate the multi-modal reference cues.
- T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing59
This paper proposes a dehazing network named T-Net, which consists of a backbone network based on the U-Net architecture and a dual attention module, and proposes a recursive strategy to take advantage of the dependence of deep features across stages via a recursion strategy.
- UNIC: Unified In-Context Video Editing58
UNified In-Context Video Editing (UNIC), a simple yet effective framework that unifies diverse video editing tasks within a single model in an in-context manner, and introduces task-aware RoPE to facilitate consistent temporal positional encoding, and condition bias that enables the model to clearly differentiate different editing tasks.
- 56
- 56
- 56
- Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding55
A Paired Rain Removal Network (PRRNet) is presented, which exploits both stereo images and semantic information, and a Semantic-Aware Deraining Module (SADM) which solves both tasks of semantic segmentation and deraining of scenes, and a Semantic-Fusion Network (SFNet) and a View-Fusion Network (VFNet) which fuse semantic information and multi-view information respectively.
- Liquid Warping GAN With Attention: A Unified Framework for Human Image Synthesis53
This paper proposes to use a 3D body mesh recovery module to disentangle the pose and shape and builds a new dataset, namely Impersonator (iPER) dataset, for the evaluation of human motion imitation, appearance transfer, and novel view synthesis.
- 52
- 49
- 47
- 46
- 46
- 45
- 45
- Coupled Network for Robust Pedestrian Detection With Gated Multi-Layer Feature Extraction and Deformable Occlusion Handling43
The proposed pedestrian detection method with a couple-network achieves promising results on both two pedestrian datasets, especially on detecting small or occluded pedestrians.
- 42
- 42
- 41
- 39
- Video Deblurring via Spatiotemporal Pyramid Network and Adversarial Gradient Prior36
A Spatiotemporal Pyramid Network is proposed to dynamically learn different spatiotemporal cues for video deblurring and a Spatiotemporal Pyramid Generative Adversarial Network (SPGAN) is proposed, which conducts adversarial discrimination in the gradient space.
- 35
- 33
- 32
- 30
- Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-Speech Gesture Generation29
This work proposes a novel weakly supervised training strategy to encourage authority gesture transitions and devise an emotion mixture mechanism that provides weak supervision based on a learnable mixed emotion label for transition gestures.
- 28
- 27
- 26
- 25
- 24
- Every Moment Matters: Detail-Aware Networks to Bring a Blurry Image Alive24
A detail-aware network with three consecutive stages to improve the reconstruction quality by addressing specific aspects in the recovery process and produces sharp image sequences with rich details and subtle motion, outperforming the state-of-the-art methods.
- 24
- 23
- 23
- 22
- Cousin Network Guided Sketch Recognition via Latent Attribute Warehouse22
This paper proposes to transfer the knowledge of a network learned from natural images to a sketch network - a new deep net architecture which is term as cousin network, which guides a sketch-recognition network to extract more relevant features that are close to those of natural images, via adversarial training.
- 20
- HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts19
HiPrompt is a new tuning-free solution that tackles the above problems by introducing hierarchical prompts, and outperforms state-of-the-art works in higher-resolution image generation, significantly reducing object repetition and enhancing structural quality.
- 19
- 19
- MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions18
This work presents MMTrail, a large-scale multi-modality video-language dataset incorporating more than 20M trailer clips with visual captions, and 2M high-quality clips with multimodal captions incorporating various modality annotations, and proposes a systemic captioning framework.
- 17
- 17
- MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results15
The developed solutions in this challenge achieved state-of-the-art performance on Few-shot RAW Image Denoising and were summarized and reviewed in this paper.
- 15
- 15
- 15
- 14
- 14
- 13
- Prompting Future Driven Diffusion Model for Hand Motion Prediction13
A prompt-based Future Driven Diffusion Model (PromptFDDM) for predicting hand motion with guidance and prompts is proposed, which achieves state-of-the-art performance in both first-and third-person perspectives.
- Homography Guided Temporal Fusion for Road Line and Marking Segmentation13
A Homography Guided Fusion module to exploit temporally-adjacent video frames for complementary cues facilitating the correct classification of the partially occluded road lines or markings is proposed and shown to lead to a light-weight network with significantly improved performances in speed and accuracy.
- 13
- 12
- Deep robust image deblurring via blur distilling and information comparison in latent space12
A latent contrastive model, Blur Distilling and Information Reconstruction Networks (BDIRNet), to learn image prior and improve the robustness of deep deblurring and achieve improved and robust results compared to recent state-of-the-art methods.
- 12
- 10
- 10
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 9
- 7
- 5
- 4
- 4
- 4
- 3
- Deep Video Restoration for Under-Display Camera3
This work proposes a novel transformer-based baseline method that adaptively enhances degraded videos of UDC-VR and builds the first large-scale UDC video restoration dataset called PexelsUDC, which includes two subsets corresponding to different displays for UDC.
- 3
- 3
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- Benchmarking Deep Deblurring Algorithms: A Large-Scale Multi-Cause Dataset and A New Baseline Model.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.