Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJanuary 2024
Learning Bilateral Cost Volume for Rolling Shutter Temporal Super-Resolution
IEEE Transactions on Pattern Analysis and Machine Intelligence (ITPM), Volume 46, Issue 5May 2024, Pages 3862–3879https://doi.org/10.1109/TPAMI.2024.3350900Rolling shutter temporal super-resolution (RSSR), which aims to synthesize intermediate global shutter (GS) video frames between two consecutive rolling shutter (RS) frames, has made remarkable progress with the development of deep convolutional neural ...
- research-articleNovember 2023
Exploring Rich Semantics for Open-Set Action Recognition
IEEE Transactions on Multimedia (TOM), Volume 262024, Pages 5410–5421https://doi.org/10.1109/TMM.2023.3333206Open-set action recognition (OSAR) aims to learn a recognition framework capable of both classifying known classes and identifying unknown actions in open-set scenarios. Existing OSAR methods typically reside in a data-driven paradigm, which ignore the ...
- research-articleNovember 2023
High-Level Data Abstraction and Elastic Data Caching for Data-Intensive AI Applications on Cloud-Native Platforms
- Rong Gu,
- Zhihao Xu,
- Yang Che,
- Xu Wang,
- Haipeng Dai,
- Kai Zhang,
- Bin Fan,
- Haojun Hou,
- Li Yi,
- Yu Ding,
- Yihua Huang,
- Guihai Chen
IEEE Transactions on Parallel and Distributed Systems (TPDS), Volume 34, Issue 11Nov. 2023, Pages 2946–2964https://doi.org/10.1109/TPDS.2023.3314659Nowdays, it is prevalent to train deep learning models in cloud-native platforms that actively leverage containerization and orchestration technologies for high elasticity, low and flexible operation cost, and many other benefits. However, it also faces ...
- ArticleJanuary 2024
Research on Script-Based Software Component Development
Green, Pervasive, and Cloud ComputingSep 2023, Pages 101–112https://doi.org/10.1007/978-981-99-9893-7_8AbstractAs software demand proliferates and software size and complexity increase, traditional software development models face enormous challenges. As a result, new software development techniques are being explored to meet the requirements of software ...
- research-articleSeptember 2023
Attention Weighted Local Descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence (ITPM), Volume 45, Issue 9Sept. 2023, Pages 10632–10649https://doi.org/10.1109/TPAMI.2023.3266728Local features detection and description are widely used in many vision applications with high industrial and commercial demands. With large-scale applications, these tasks raise high expectations for both the accuracy and speed of local features. Most ...
-
- research-articleJune 2023
Presto: A Decade of SQL Analytics at Meta
- Yutian Sun,
- Tim Meehan,
- Rebecca Schlussel,
- Wenlei Xie,
- Masha Basmanova,
- Orri Erling,
- Andrii Rosa,
- Shixuan Fan,
- Rongrong Zhong,
- Arun Thirupathi,
- Nikhil Collooru,
- Ke Wang,
- Sameer Agarwal,
- Arjun Gupta,
- Dionysios Logothetis,
- Kostas Xirogiannopoulos,
- Amit Dutta,
- Varun Gajjala,
- Rohit Jain,
- Ajay Palakuzhy,
- Prithvi Pandian,
- Sergey Pershin,
- Abhisek Saikia,
- Pranjal Shankhdhar,
- Neerad Somanchi,
- Swapnil Tailor,
- Jialiang Tan,
- Sreeni Viswanadha,
- Zac Wen,
- Biswapesh Chattopadhyay,
- Bin Fan,
- Deepak Majeti,
- Aditi Pandit
Proceedings of the ACM on Management of Data (PACMMOD), Volume 1, Issue 2Article No.: 189, Pages 1–25https://doi.org/10.1145/3589769Presto is an open-source distributed SQL query engine that supports analytics workloads involving multiple exabyte-scale data sources. Presto is used for low-latency interactive use cases as well as long-running ETL jobs at Meta. It was originally ...
- research-articleJune 2023
Learning Proposal-Aware Re-Ranking for Weakly-Supervised Temporal Action Localization
IEEE Transactions on Circuits and Systems for Video Technology (IEEETCSVT), Volume 34, Issue 1Jan. 2024, Pages 207–220https://doi.org/10.1109/TCSVT.2023.3283430Weakly-supervised temporal action localization (WTAL) aims to localize and classify action instances in untrimmed videos with only video-level labels available. Despite the remarkable success of existing methods, whose generated proposals are commonly far ...
- research-articleJune 2023
DomainFeat: Learning Local Features With Domain Adaptation
IEEE Transactions on Circuits and Systems for Video Technology (IEEETCSVT), Volume 34, Issue 1Jan. 2024, Pages 46–59https://doi.org/10.1109/TCSVT.2023.3282956Accurate and efficient keypoint detection and description is a fundamental step in various computer vision tasks. In this paper, we extract robust descriptors and detect accurate keypoints by learning local Features with Domain adaptation (DomainFeat). ...
- research-articleApril 2023
Rolling Shutter Inversion: Bring Rolling Shutter Images to High Framerate Global Shutter Video
IEEE Transactions on Pattern Analysis and Machine Intelligence (ITPM), Volume 45, Issue 5May 2023, Pages 6214–6230https://doi.org/10.1109/TPAMI.2022.3212912A single rolling-shutter (RS) image may be viewed as a row-wise combination of a sequence of global-shutter (GS) images captured by a (virtual) moving GS camera within the exposure duration. Although rolling-shutter cameras are widely used, the RS effect ...
- research-articleMarch 2023
Graphene: An IR for Optimized Tensor Computations on GPUs
ASPLOS 2023: Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3March 2023, Pages 302–313https://doi.org/10.1145/3582016.3582018Modern GPUs accelerate computations and data movements of multi-dimensional tensors in hardware. However, expressing optimized tensor computations in software is extremely challenging even for experts. Languages like CUDA C++ are centered around flat ...
- research-articleJanuary 2023
Seeing Through Darkness: Visual Localization at Night via Weakly Supervised Learning of Domain Invariant Features
IEEE Transactions on Multimedia (TOM), Volume 252023, Pages 1713–1726https://doi.org/10.1109/TMM.2022.3154165Long term visual localization has to conquer the problem of matching images with dramatic photometric changes caused by different seasons, natural and man-made illumination changes, etc. Visual localization at night plays a vital role in many applications ...
- research-articleNovember 2022
Incremental Translation Averaging
IEEE Transactions on Circuits and Systems for Video Technology (IEEETCSVT), Volume 32, Issue 11Nov. 2022, Pages 7783–7795https://doi.org/10.1109/TCSVT.2022.3183631Translation averaging is known to be more difficult than rotation averaging due to scale ambiguity, estimation sensitivity, and solution uncertainty. Existing approaches have exposed their limitations in terms of accuracy, robustness, simplicity, or ...
- research-articleNovember 2022
DSLA: Dynamic smooth label assignment for efficient anchor-free object detection
Highlights- The inconsistencies of classification and quality estimation are analyzed. Dynamic smooth label assignment is proposed to address the problems.
Anchor-free detectors basically formulate object detection as dense classification and regression. For popular anchor-free detectors, it is common to introduce an individual prediction branch to estimate the quality of localization. ...
- research-articleNovember 2022
Robust self-supervised monocular visual odometry based on prediction-update pose estimation network
Engineering Applications of Artificial Intelligence (EAAI), Volume 116, Issue CNov 2022https://doi.org/10.1016/j.engappai.2022.105481AbstractVisual odometry aims at estimating the camera pose from video sequence, which is an important part of visual Simultaneous Localization and Mapping (SLAM). In this paper, we propose a novel prediction-update pose estimation network, PU-...
- ArticleOctober 2022
Out-of-distribution Detection with Boundary Aware Learning
AbstractThere is an increasing need to determine whether inputs are out-of-distribution (OOD) for safely deploying machine learning models in the open world scenario. Typical neural classifiers are based on the closed world assumption, where the training ...
- ArticleOctober 2022
- ArticleOctober 2022
CARR-Net: Leveraging on Subtle Variance of Neighbors for Point Cloud Semantic Segmentation
Pattern Recognition and Computer VisionOct 2022, Pages 124–136https://doi.org/10.1007/978-3-031-18913-5_10AbstractFor 3D semantic segmentation task, how to fully explore intrinsic feature of point cloud is worthy to be well considered. We note that neighboring points used for representing local structure of a 3D point are usually very close to the point which ...
- research-articleOctober 2022
Time identification of design knowledge push based on cognitive load measurement
Advanced Engineering Informatics (ADEI), Volume 54, Issue COct 2022https://doi.org/10.1016/j.aei.2022.101783Highlights- Current knowledge acquisition approaches for product design have been reviewed.
- Behavioral indicators related to changes in cognitive load are identified.
- The efficacy of inferring the cognitive load based on behavioral indicators ...
The reuse of multidisciplinary design knowledge is pivotal in product development because of the increasingly fierce market competition. It can assist designers, particularly those who lack sufficient experience, in making correct decisions and ...
- research-articleAugust 2022
VRNet: Learning the Rectified Virtual Corresponding Points for 3D Point Cloud Registration
IEEE Transactions on Circuits and Systems for Video Technology (IEEETCSVT), Volume 32, Issue 8Aug. 2022, Pages 4997–5010https://doi.org/10.1109/TCSVT.2022.31431513D point cloud registration is fragile to outliers, which are labeled as the points without corresponding points. To handle this problem, a widely adopted strategy is to estimate the relative pose based only on some accurate correspondences, which is ...
- research-articleAugust 2022
Differential SfM and image correction for a rolling shutter stereo rig
Image and Vision Computing (IAVC), Volume 124, Issue CAug 2022https://doi.org/10.1016/j.imavis.2022.104492Highlights- A simple and flexible generalized RS stereo differential SfM algorithm over two consecutive frames.
Most modern consumer-grade cameras are equipped with an electronic rolling shutter (RS), leading to image distortions when the camera moves during image acquisition. We explore the first structure and motion estimation problem of a ...