Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks170 from public data
- 1,776
- 959
- Learning a no-reference quality metric for single-image super-resolution625
Three types of low-level statistical features in both spatial and frequency domains are designed to quantify super-resolved artifacts and a two-stage regression model is learned to predict the quality scores of super-resolution images without referring to ground-truth images.
- Single-Image Super-Resolution: A Benchmark615
A systematic benchmark evaluation for state-of-the-art single-image super-resolution algorithms based on conventional full-reference metrics and human subject studies to evaluate image quality based on visual perception is presented.
- Depth-Aware Video Frame Interpolation596
A video frame interpolation method which explicitly detects the occlusion by exploring the depth information, and develops a depth-aware flow projection layer to synthesize intermediate flows that preferably sample closer objects than farther ones.
- VITAL: VIsual Tracking via Adversarial Learning577
The VITAL algorithm is presented, which uses a generative network to randomly generate masks, which are applied to adaptively dropout input features to capture a variety of appearance changes and identifies the mask that maintains the most robust features of the target objects over a long temporal span.
- CREST: Convolutional Residual Learning for Visual Tracking562
This paper proposes the CREST algorithm to reformulate DCFs as a one-layer convolutional neural network, and applies residual learning to take appearance changes into account to reduce model degradation during online update.
- See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks537
This work introduces a novel network, called as CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view and proposes a unified and end-to-end trainable framework where different co-att attention variants can be derived for mining the rich context within videos.
- 506
- 496
- Target-Aware Deep Tracking450
This paper develops a regression loss and a ranking loss to guide the generation of target-active and scale-sensitive features and proposes a novel scheme to learn target-aware features, which can better recognize the targets undergoing significant appearance variations than pre-trained deep features.
- 449
- Unsupervised Deep Tracking416
The proposed unsupervised tracker achieves the baseline accuracy of fully supervised trackers, which require complete and accurate labels during training, and exhibits a potential in leveraging unlabeled or weakly labeled data to further improve the tracking accuracy.
- 351
- Deep Regression Tracking with Shrinkage Loss243
This work proposes a novel shrinkage loss to penalize the importance of easy training data and applies residual connections to fuse multiple convolutional layers as well as their output response maps to balance training data.
- 226
- Robust Visual Tracking via Hierarchical Convolutional Features208
This paper interprets the hierarchical features of convolutional layers as a nonlinear counterpart of an image pyramid representation and explicitly exploit these multiple levels of abstraction to represent target objects to improve the accuracy and robustness of visual tracking.
- Single-Model and Any-Modality for Video Object Tracking172
This work introduces Un-Track, a Unified Tracker of a single set of parameters for any modality, which surpasses both SOTA unified trackers and modality-specific counterparts, validating the effectiveness and practicality.
- Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking161
This paper proposes to learn multiple adaptive correlation filters with both long-term and short-term memory of target appearance for robust object tracking and demonstrates that the proposed algorithm performs favorably against the state-of-the-art methods in terms of efficiency, accuracy, and robustness.
- HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness158
This paper proposes a novel Hierarchical Depth Awareness network (HiDAnet) for RGB-D saliency detection, and uses a granularity-based attention scheme to strengthen the discriminatory power of RGB and depth features separately and introduces a unified cross dual-attention module for multi-modal and multi-level fusion in a coarse-to-fine manner.
- SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction132
SarseOcc is proposed, an efficient occupancy network inspired by sparse point cloud processing that achieves a remarkable 74.9% reduction on FLOPs over the dense baseline and improves accuracy, from 12.8% to 14.1% mIOU, which can be attributed to the sparse representation's ability to avoid hallucinations on empty voxels.
- 130
- Unsupervised Deep Representation Learning for Real-Time Tracking125
This work proposes an unsupervised learning method for visual tracking that achieves the baseline accuracy of classic fully supervised trackers while achieving a real-time speed and exhibits a potential in leveraging more unlabeled or weakly labeled data to further improve the tracking accuracy.
- Visual Question Answering with Memory-Augmented Networks112
It is shown that memory-augmented neural networks are able to maintain a relatively long-term memory of scarce training exemplars, which is important for visual question answering due to the heavy-tailed distribution of answers in a general VQA setting.
- 104
- Exploring Frequency Adversarial Attacks for Face Forgery Detection101
This paper proposes a frequency adversarial attack method against face forgery detectors that fools not only the spatial-based detectors but also the state-of- the-art frequency-based detector effectively and enhances the transferability across face forgeries detectors as black-box attacks.
- 93
- UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View87
A universal cross-modality knowledge distillation framework (UniDistill) to improve the performance of single- modality detectors by projects the features of both the teacher and the student detector into Bird's-Eye-View (BEV), which is a friendly representation for different modalities.
- 87
- IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking75
A decision-based black-box attack method for visual object tracking that sequentially generates perturbations based on the predicted IoU scores from both current and historical frames is proposed and validated on state-of-the-art deep trackers.
- Language-Guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning72
A cross-modal grounding module is designed, which is composed of two complementary attention mechanisms, to equip the agent with a better ability to track the correspondence between the textual and visual modalities and further exploit the advantages of both these two learning schemes via adversarial learning.
- End-to-End Learning Deep CRF Models for Multi-Object Tracking Deep CRF Models71
This paper proposes learning deep conditional random field networks, aiming to model the assignment costs as unary potentials and the long-term dependencies among detection results as pairwise potentials, and poses the CRF inference as a recurrent neural network learning process using the standard gradient descent algorithm.
- Learning to Track Objects from Unlabeled Videos66
Extensive experiments show that the proposed USOT learned from unlabeled videos performs well over the state-of-the-art unsupervised trackers by large margins, and on par with recent supervised deep trackers.
- Robust Tracking Against Adversarial Attacks66
This work first attempts to generate adversarial examples on top of video sequences to improve the tracking robustness against adversarial attacks, and applies the proposed adversarial attack and defense approaches to state-of-the-art deep tracking algorithms.
- Rethinking Image Deraining via Rain Streaks and Vapors62
This work reformulate rain streaks as transmission medium together with vapors to model rain imaging and proposes an encoder-decoder CNN named as SNet to learn the transmission map of rain streaks and a VNet containing spatial pyramid pooling to predict the Transmission map of vapors in multi-scales based on that ofRain streaks.
- 62
- Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering56
This paper uses adversarial learning to train a classic VQA model (BUTD) with augmented data, and finds that it not only improves the overall performance on VQAv2, but also can withstand adversarial attack effectively, compared to the baseline model.
- Facial Geometric Detail Recovery via Implicit Representation55
This work presents a robust texture-guided geometric detail recovery approach using only a single in-the-wild facial image and registers the implicit shape details to a 3D Morphable Model template, which can be used in traditional modeling and rendering pipelines.
- 54
- 48
- 46
- 44
- 43
- Combined Application of Bacteriophages and Carvacrol in the Control of Pseudomonas syringae pv. actinidiae Planktonic and Biofilm Forms43
The combined treatment with phages and carvacrol may be a promising, environment-friendly and cost-effective approach to controlling Psa in the kiwifruit industry.
- 42
- 41
- Cross-Modality 3D Object Detection40
This paper presents a novel two-stage multi-modal fusion network for 3D object detection, taking both binocular images and raw point clouds as input, and proposes to use pseudo LiDAR points from stereo matching as a data augmentation method to densify the LiDar points.
- 40
- Characterization of a Lytic Bacteriophage against Pseudomonas syringae pv. actinidiae and Its Endolysin40
Characteristics demonstrate that the phage PN09 and its endolysin, LysPN09, are potential candidates for biocontrol of Psa in the kiwifruit industry.
- Power transformer fault diagnosis system based on Internet of Things39
The technical support of the Internet of Things is helpful to the upgrading and maintenance of the power transformer fault diagnosis system and can be seen that the technical support of the Internet of Things is helpful to the upgrading and maintenance of the power transformer fault diagnosis system.
- 34
- 33
- Learning transform-aware attentive network for object tracking33
A transform-aware attentive tracking framework, which uses a deep attentive network to directly predict the target states via spatial transform parameters, built on the Spatial Transform Network (STN).
- Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane31
Frankenstein, a diffusion-based framework that can generate semantic-compositional 3D scenes in a single pass, demonstrates promising results in generating room interiors as well as human avatars with automatically separated parts.
- 30
- 29
- 28
- Towards Unified Defense for Face Forgery and Spoofing Attacks via Dual Space Reconstruction Learning26
- 25
- 25
- 23
- What You Have is What You Track: Adaptive and Robust Multimodal Tracking22
This paper proposes a flexible framework for robust multimodal tracking through a novel Heterogeneous Mixture-of-Experts fusion mechanism with adaptive complexity, coupled with a video-level masking strategy that ensures both temporal consistency and spatial completeness - critical for effective video tracking.
- 22
- 20
- 20
- 19
- 19
- 16
- 16
- 16
- 14
- 13
- 13
- 12
- 12
- 11
- 10
- 10
- 9
- 8
- 8
- 7
- 7
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Research on Architecture and Key Technology of Fault Prognostics and Health Management for Equipment1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-13. 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.