Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks40 from public data
- DeepHunter: a coverage-guided fuzz testing framework for deep neural networks480
DeepHunter, a coverage-guided fuzz testing framework for detecting potential defects of general-purpose DNNs, is proposed and a metamorphic mutation strategy to generate new semantically preserved tests is proposed, and multiple extensible coverage criteria as feedback to guide the test generation.
- ARID: A New Dataset for Recognizing Action in the Dark98
It is shown that current action recognition models and frame enhancement methods may not be effective solutions for the task of action recognition in dark videos.
- Continual Semantic Segmentation with Automatic Memory Sample Selection85
This work proposes a novel memory sample selection mechanism that selects informative samples for effective replay in a fully automatic way by considering comprehensive factors including sample diversity and class performance.
- Learning Gabor Texture Features for Fine-Grained Recognition65
This work innovatively utilizes Gabor filters as a powerful extractor to exploit texture features, motivated by the capability of Gabor filter in effectively capturing multi-frequency features and detailed local information.
- Towards Building AI-CPS with NVIDIA Isaac Sim: An Industrial Benchmark and Case Study for Robotics Manipulation52
This work establishes a foundation for the design and development of AI-enabled robotics systems but also provides practical experience and guidance to practitioners in this field, promoting further research in this critical academic and industrial domain.
- ACT: an Attentive Convolutional Transformer for Efficient Text Classification47
An Attentive Convolutional Transformer (ACT) is introduced that takes the advantages of both Transformer and CNN for efficient text classification, and is able to capture both local and global dependencies effectively while preserving sequential information.
- Improving Deep Lesion Detection Using 3D Contextual and Spatial Attention41
A dual-attention mechanism to the 3D contextual lesion detection framework is introduced, including the cross-slice contextual attention to selectively aggregate the information from different slices through a soft re-sampling process, and intra-slice spatial attention to focus the feature learning in the most prominent regions.
- 40
- 31
- MLModelCI: An Automatic Cloud Platform for Efficient MLaaS30
A key feature of MLModelCI is the implementation of a controller, which allows elastic evaluation which only utilizes idle workers while maintaining online service quality and thus free developers from manual and tedious work often associated with service deployment.
- Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks29
This work proposes a novel approach for cost-adjustable inference in CNNs - Stochastic Downsampling Point (SDPoint), which is validated through extensive experiments on image classification.
- 25
- 18
- Towards Balanced Active Learning for Multimodal Classification15
A novel approach is proposed to achieve more fair data selection by modulating the gradient embedding with the dominance degree among modalities and outperforms existing active learning strategies on a variety of multimodal classification tasks.
- Exploiting inter-frame regional correlation for efficient action recognition13
This paper proposes a novel temporal feature extraction method, named Attentive Correlated Temporal Feature (ACTF), by exploring inter-frame correlation within a certain region and has the advantage of achieving performance comparable to or better than optical flow-based methods while avoiding the introduction of optical flow.
- Saving the Limping: Fault-tolerant Quadruped Locomotion via Reinforcement Learning12
A novel methodology to train and test hardware fault-tolerant controllers for quadruped locomotion, both in the simulation and physical world is proposed, which adopts the teacher-student reinforcement learning framework to train the controller with close-to-reality joint-locking failure in the Simulation.
- Cloud3DView: an interactive tool for cloud data center operations12
A novel cloud data center management system is designed and built, based on the concept of 3D gamification, allowing the operators to monitor the real-time situation and control the data center from a friendly user interface.
- 11
- Transforming Future Data Center Operations and Management via Physical AI10
This research proposes a novel physical AI (PhyAI) framework to advance DC operations and management that enables the creation of real-time digital twins to digitalize, optimize, and automate future DC operations.
- 10
- MIGPerf: A Comprehensive Benchmark for Deep Learning Training and Inference Workloads on Multi-Instance GPUs10
MIGPerf is presented, an open-source tool that streamlines the benchmark study for MIG and provides new insights and guidance for users to effectively employ MIG, and lays the foundation for further research on the orchestration of hybrid training and inference workloads on MIGs.
- Early Temporal Dynamics of Gonadal Development and Sexually Dimorphic Gene Expression During Sex Differentiation in Mandarin Fish (Siniperca chuatsi)9
It is confirmed that sex determination in mandarin fish occurs before 27 dpf, whereas in males, it occurs from 33 to 57 dpf and in females, sex differentiation progresses from 27 to 51 dpf, whereas in males, it occurs from 33 to 57 dpf.
- Self-Supervised Video Representation Learning by Video Incoherence Detection8
A novel self-supervised method that leverages incoherence detection for video representation learning and introduces intravideo contrastive learning to maximize the mutual information between incoherent clips from the same raw video.
- Effective action recognition with embedded key point shifts8
This paper proposes a novel temporal feature extraction module, named Key Point Shifts Embedding Module ($KPSEM$), to adaptively extract channel-wise key point shifts across video frames without key point annotation for temporal features extraction.
- 8
- Going Deeper into Recognizing Actions in Dark Environments: A Comprehensive Benchmark Study7
This work focuses on the task of action recognition in dark environments, which can be applied to fields such as surveillance and autonomous driving at night and evaluates and advances the robustness of AR models in dark environments.
- PNL: Efficient long-range dependencies extraction with pyramid non-local module for action recognition7
Pyramid Non-Local (PNL) module is proposed, which extends the non-local block by incorporating regional correlation at multiple scales through a pyramid structured module, which upscales the effectiveness of non- local operation by attending to the interaction between different regions.
- 7
- A context-rich and extensible framework for spontaneous smartphone networking6
A place-learning algorithm using the properties of scanned Wi-Fi access points to identify meaningful places and is implemented on Android-based, off-the-shelf smartphones without any adaptation of their networking architecture.
- Evolving a Deep Neural Network Training Time Estimator5
Results show that despite the low degree of information in the representation and the simple initial design for the predictor, co-evolving the training set performs better than near random generated population of DNNs.
- No more 996: Understanding Deep Learning Inference Serving with an Automatic Benchmarking System.4
This work implements an automatic and comprehensive benchmark system for DL developers to expedite day-to-day DL service evaluation efforts by the developers and conducts many benchmark experiments to provide in-depth and comprehensive evaluations.
- Unified Locomotion Transformer with Simultaneous Sim-to-Real Transfer for Quadrupeds3
Evaluation results demonstrate that with ULT, optimal teacher and student policies can be obtained at the same time, greatly easing the difficulty in knowledge transfer, even with complex transformer-based models.
- Masked Sensory-Temporal Attention for Sensor Generalization in Quadruped Locomotion3
MSTA employs direct sensor-level attention to enhance the sensory-temporal understanding and handle different combinations of sensor data, serving as a foundation for incorporating unseen information.
- Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning2
This research develops a two-stage method for Multi-Modal Cold-Start Active Learning (MMCSAL), and proposes enhancing cross-modal alignment through regularization, thereby improving the quality of selected multimodal data pairs in AL.
- 2
- Transient data delivery using fine‐grained mobility data in spontaneous smartphone networks1
This paper introduces a Markov predictor-based transient delivery scheme that quantifies the regularity of small time scale movement for forwarding decisions that outperforms compared alternatives in terms of delivery rate and cost.
- –
- Scalable AI Computing Lifecycle–
An overview of typical AI computing tasks lifecycle is given, a few representative large scale AI computing projects are case study, and system bottlenecks and potential techniques that can allow more efficient AI computing for scaling out are explained.
- –
- –
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 2026-10-12. 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.