Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks95 from public data
- The Sixth Visual Object Tracking VOT2018 Challenge Results804
The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative; results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years.
- GradNet: Gradient-Guided Network for Visual Object Tracking334
A novel gradient-guided network to exploit the discriminative information in gradients and update the template in the siamese network through feed-forward and backward operations and a template generalization training method is proposed to better use gradient information and avoid overfitting.
- 279
- Real-Time ‘Actor-Critic’ Tracking139
This work modifications the original deep deterministic policy gradient algorithm to effectively train the ‘Actor-Critic’ model for the tracking task and demonstrates that the proposed tracker performs favorably against many state-of-the-art methods, with real-time performance.
- GLiT: Neural Architecture Search for Global and Local Image Transformer107
This work introduces the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition and introduces a locality module that models the local correlations in images explicitly with fewer computational cost.
- Multi attention module for visual tracking75
This work proposes a new visual tracking algorithm leveraging multi-level visual attention to take full use of the information during tracking, and implements the attention network with long short term memory (LSTM) units, which are capable of capturing the historical context information to perform more reliable inference at the current time step.
- 62
- 54
- Evolving Search Space for Neural Architecture Search51
The proposed NSE scheme achieves 77.3% top-1 retrain accuracy on ImageNet with 333M FLOPs, which yielded a state-of-the-art performance among previous auto-generated architectures that do not involve knowledge distillation or weight pruning.
- BN-NAS: Neural Architecture Search with Batch Normalization37
BN-NAS can significantly reduce the time required by model training and evaluation in NAS and a BN-based indicator for predicting subnet performance at a very early training stage is proposed for fast evaluation.
- An IoT-based smart mosquito trap system embedded with real-time mosquito image processing by neural networks for mosquito surveillance36
A smart mosquito trap system to reduce the density of mosquito vectors and the spread of mosquito-borne diseases using computer vision technology and deep learning networks to identify features of live Aedes aegypti and Culex quinquefasciatus in real-time is designed.
- Disruption of thalamic connectivity in Alzheimer’s disease: a diffusion tensor imaging study30
The DTI analyses indicate that the integrity of thalamic connectivity is progressively disrupted following cognitive decline in AD and that DTI parameters in the column and body of the fornix show promise as potential markers for the early diagnosis of AD and for monitoring disease progression.
- 29
- 26
- 20
- 18
- 17
- Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks13
A data-driven approach that uses a generative adversarial network to create the song transition by learning from real-world DJ mixes to achieve competitive results compared with a number of baselines is explored.
- 13
- 12
- 12
- 10
- 9
- 8
- 8
- 8
- 7
- 7
- Exploiting Pre-trained Feature Networks for Generative Adversarial Networks in Audio-domain Loop Generation7
This paper investigates whether Projected GAN can similarly improve audio generation, by evaluating the performance of a StyleGAN2-based audio-domain loop generation model with and without using a pre-trained feature space in the discriminator.
- Visual tracking by dynamic matching-classification network switching7
This work presents a novel real-time robust tracking method to take full use of the benefits from both kinds of networks, and proposes a matching-classification network switching (MCS) framework to integrate the matching, classification, verification networks and conduct dynamic switching among them.
- 6
- A Study on Educational Technology Acceptance of Special Education Teachers in Language Teaching Based on TAM Model6
Suggestions are put forward on the future of application of technology in special education from the three stages (identification & evaluation, training support and technical assistance) and two elements (family engagement and differentiated instruction).
- Use of unmanned ground vehicle systems in urbanized zones: A study of vector Mosquito surveillance in Kaohsiung6
Improved the high-resolution digital camera and spraying system of the UGVs may be able to effectively and instantly monitor vector mosquitoes and implement spraying controls, and may be suitable to solve the complex and difficult task of detecting mosquito breeding sources in urban ditches.
- Design and Validation of a Route Planner for Logistic UAV Swarm5
In this study, a group of five multicopters was set up to validate the swarm system, and the result shows that the improved 2TS+2OPT is able to converge to a better solution that allows logistic UAV swarms to operate in a more efficient way.
- 2 × 2 optofluidic switch chip with an air shutter5
The research results show that the microchannel width has great influence on the switch performances in "on" state, where the comprehensive performances of the optical switch are the best at 4.0 μm width.
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- Interpretable adversarial neural pairwise ranking for academic network embedding3
This study addresses the gap in adversarial neural Bayesian ranking-based academic network embedding by introducing the adversarial neural Bayesian ranking-based academic network embedding (Adversarial Neural-Brane).
- 3
- Deep recommendation with iteration directional adversarial training3
A Deep Recommender with Iteration Directional Adversarial Training (DRIDAT) that combines attention mechanism and directional adversarial training for recommendations is proposed that outperforms all other methods for all metrics.
- 3
- 3
- Failure-Robot Path Complementation for Robot Swarm Mission Planning3
The aim of the present study was to develop a multiple-vehicle system that can automatically compile a set of optimum vehicle paths, complement failed assignments, and avoid passing through no-travel zones.
- 3
- Optic Nerve Sheath Dural Arteriovenous Fistula Mimicking Carotid Cavernous Fistula3
This work aims to provide a history of ophthalmology in China and its role in modern medicine by establishing a chronology of key events leading to blindness and the types of injuries experienced by patients.
- 3
- 2
- SPERM: sequential pairwise embedding recommendation with MI-FGSM2
The proposed SPERM model is proposed, a model that incorporates visual, temporal, and sequential information for visual recommendations through adversarial training that fortify the SPERM approach with adversarial training, where the primary objective is to train the model to withstand adversarial inputs introduced by MI-FGSM.
- 2
- 2
- 2
- 2
- Face Recognition from Depth Images with Convolutional Neural Network2
A Convolutional Neural Network structure for face recognition in depth images is proposed and experiments show that the proposed CNN structure can significantly improve the face recognition accuracy, compared with traditional face recognition methods, such as LBP, moment invariant and PCA.
- 2
- 1
- Bioorthogonal Probe BTD-Az Enables Sensitive and Rapid In Vivo Profiling of Protein Cysteine Sulfenylation1
The design and application of BTD-Az, a cell-permeable probe that incorporates an azide handle into the benzothiazine scaffold, are reported, enabling rapid bioorthogonal labeling of Cys–SOH both in vivo and in vitro, followed by efficient enrichment through strain-promoted azide-alkyne cycloaddition.
- 1
- 1
- 1
- 1st Place Solutions for the UVO Challenge 20221
The method ranks first on the 2nd Unidentified Video Objects (UVO) challenge, achieving AR@100 of 46.8, 64.7 and 32.2 in the limited data frame track, unlimited data frame track and video track respectively.
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- Establishing a noncanonical zinc-binding group as a selective histone deacetylase inhibitor and possible novel anticancer agent–
Building on the core structure of the highly selective HDAC6 inhibitor J22352, various zinc-binding groups of this inhibitor were modified and designed and synthesized to explore potential derivatives and assess their effects on NSCLC bioactivity.
- –
- Efficacy of catheter-based ultrasound renal denervation in the treatment of hypertension–
The current evidence suggests that uRDN may effectively reduce home, office, and daytime blood pressure (SBP) in patients with HTN, particularly in those with non-resistant HTN.
- –
- –
- –
- –
- –
- –
- –
- –
- SWU-NIRPV: a near-infrared pose variation face database and pose-invariant face recognition–
An NIR face database with 57 pose variations in a dark environment, which can be used in pose-invariant FR research and showed that a difference of even 10 deg between the gallery and testing sets can dramatically reduce the recognition performance.
- –
- –
- –
- –
- Social Search Technique with the Consideration of User Location–
This research proposes a social search architecture based on the data from Facebook with the combination of term frequency and location information as the criteria of ranking.
- –
- –
- Video compression by bit‐plane watermarking–
It is shown that the scheme successfully detects changes made to the content of MPEG‐4 FGS video streams and identifies the specific location at which these changes have been made and can further reduce the length of compressed bit stream.
- An Instructional Model for Learning Theorem Proving with Dynamic Geometry Environment–
An instructional model using a dynamic geometry environment that integrates the elements of exploration and theorem proving is proposed to address issues of poor understanding and ignorance of intermediate geometric propositions.
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 2026-10-14. 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.