Recently, Spectral Compressive Imaging (SCI) has achieved remarkable success, unlocking significant potential for dynamic spectral vision. However, existing reconstruction methods, primarily image-based, suffer from two limitations: (i) Encoding process masks spatial-spectral features, leading to uncertainty in reconstructing missing information from single compressed measurements, and (ii) The frame-by-frame reconstruction paradigm fails to ensure temporal consistency, which is crucial in the video perception. To address these challenges, this paper seeks to advance spectral reconstruction from the image level to the video level, leveraging the complementary features and temporal continuity across adjacent frames in dynamic scenes. Initially, we construct the first high-quality dynamic hyperspectral image dataset (DynaSpec), comprising 30 sequences obtained through frame-scanning acquisition. Subsequently, we propose the Propagation-Guided Spectral Video Reconstruction Transformer (PG-SVRT), which employs a spatial-then-temporal attention to effectively reconstruct spectral features from abundant video information, while using a bridged token to reduce computational complexity. Finally, we conduct simulation experiments to assess the performance of four SCI systems, and construct a DD-CASSI prototype for real-world data collection and benchmarking. Extensive experiments demonstrate that PG-SVRT achieves superior performance in reconstruction quality, spectral fidelity, and temporal consistency, while maintaining minimal FLOPs. Project page: https://github.com/nju-cite/DynaSpec
University of Bath（巴斯大学）；Imago7 foundation（Imago7基金会）；University of Edinburgh（爱丁堡大学）；GE Healthcare（GE医疗）；Technical University of Munich（慕尼黑工业大学）
We propose a dictionary-matching-free pipeline for multi-parametric quantitative MRI image computing. Our approach has two stages based on compressed sensing reconstruction and deep learned quantitative inference. The reconstruction phase is convex and incorporates efficient spatiotemporal regularisations within an accelerated iterative shrinkage algorithm. This minimises the under-sampling (aliasing) artefacts from aggressively short scan times. The learned quantitative inference phase is purely trained on physical simulations (Bloch equations) that are flexible for producing rich training sa…
STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene
National Key Lab of Multispectral Information Intelligent Processing Technology（多谱信息智能处理国家级重点实验室）；School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（人工智能与自动化学院，华中科技大学）；School of Computing, National University of Singapore（计算机学院，新加坡国立大学）
DengueNet: Dengue Prediction using Spatiotemporal Satellite Imagery for Resource-Limited Countries
Massachusetts Institute of Technology（麻省理工学院）；Harvard University（哈佛大学）；University College Dublin（都柏林大学学院）；University of Cauca（考卡大学）；Indiana University – Purdue University Indianapolis（印第安纳大学与普渡大学印第安纳波利斯联合分校）；Worcester Polytechnic Institute（伍斯特理工学院）；Beth Israel Deaconess Medical Center（贝斯以色列女执事医疗中心）
MS-LSTM: Exploring Spatiotemporal Multiscale Representations in Video Prediction Domain
Faculty of Computing, Harbin Institute of Technology（哈尔滨工业大学计算机学院）；International Research Institute for Artificial Intelligence, Harbin Institute of Technology（哈尔滨工业大学国际人工智能研究院）
Hong Kong University of Science and Technology（香港科技大学）；Amazon Web Services（亚马逊云科技）；Rutgers University（罗格斯大学）
Conventionally, Earth system (e.g., weather and climate) forecasting relies on numerical simulation with complex physical models and are hence both expensive in computation and demanding on domain expertise. With the explosive growth of the spatiotemporal Earth observation data in the past decade, data-driven models that apply Deep Learning (DL) are demonstrating impressive potential for various Earth system forecasting tasks. The Transformer as an emerging DL architecture, despite its broad success in other domains, has limited adoption in this area. In this paper, we propose Earthformer, a s…
Multi-scale Restoration of Missing Data in Optical Time-series Images with Masked Spatial-Temporal Attention Network
School of Computer Science, China University of Geosciences（中国地质大学（武汉）计算机学院）；Engineering Research Center of Natural Resource Information Management and Digital Twin Engineering Software, Ministry of Education（教育部自然资源信息管理与数字孪生工程软件工程研究中心）；Second Surveying and Mapping Institute of Hunan Province（湖南省第二测绘院）；Key Laboratory of Natural Resources Monitoring and Supervision in Southern Hilly Region, Ministry of Natural Resources（自然资源部南方山地自然资源监测与监管重点实验室）
SOKENDAI (Graduate University for Advanced Studies)（综合研究大学院大学）；National Institute of Informatics（国立信息学研究所）
Detecting salient objects from a video requires exploiting both spatial and temporal knowledge included in the video. We propose a novel region-based multiscale spatiotemporal saliency detection method for videos, where static features and dynamic features computed from the low and middle levels are combined together. Our method utilizes such combined features spatially over each frame and, at the same time, temporally across frames using consistency between consecutive frames. Saliency cues in our method are analyzed through a multiscale segmentation model, and fused across scale levels, yiel…
Exploring Adaptive Masked Reconstruction for Self-Supervised Skeleton-Based Action Recognition
Hefei University of Technology（合肥工业大学）；Jilin University（吉林大学）；Zhejiang Gongshang University（浙江工商大学）；University of Science and Technology of China（中国科学技术大学）
SeasFire as a Multivariate Earth System Datacube for Wildfire Dynamics
National Observatory of Athens（雅典国家天文台）；Max Planck Institute for Biogeochemistry（马克斯·普朗克生物地球化学研究所）；Universitat de València（瓦伦西亚大学）；University of Cambridge（剑桥大学）；Universidade Nova de Lisboa（新里斯本大学）；National Technical University of Athens（雅典国家技术大学）
Dynamic and Compressive Adaptation of Transformers From Images to Videos
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；Platform and Content Group (PCG), Tencent（腾讯平台与内容事业群）；Shanghai AI Lab（上海人工智能实验室）
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Peking University（北京大学）；Information Technology R&D Innovation Center of Peking University（北京大学信息技术创新研发中心）
Video prediction aims to predict future frames by modeling the complex spatiotemporal dynamics in videos. However, most of the existing methods only model the temporal information and the spatial information for videos in an independent manner but haven't fully explored the correlations between both terms. In this paper, we propose a SpatioTemporal-Aware Unit (STAU) for video prediction and beyond by exploring the significant spatiotemporal correlations in videos. On the one hand, the motion-aware attention weights are learned from the spatial states to help aggregate the temporal states in th…
Huazhong University of Science and Technology（华中科技大学）；Essex University（埃塞克斯大学）；Hong Kong University of Science and Technology（香港科技大学）
Deep learning has shown impressive performance in semantic segmentation, but it is still unaffordable for resource-constrained mobile devices. While offloading computation tasks is promising, the high traffic demands overwhelm the limited bandwidth. Existing compression algorithms are not fit for semantic segmentation, as the lack of obvious and concentrated regions of interest (RoIs) forces the adoption of uniform compression strategies, leading to low compression ratios or accuracy. This paper introduces STAC, a DNN-driven compression scheme tailored for edge-assisted semantic video segmenta…
A steady momentum of innovations and breakthroughs has convincingly pushed the limits of unsupervised image representation learning. Compared to static 2D images, video has one more dimension (time). The inherent supervision existing in such sequential structure offers a fertile ground for building unsupervised learning models. In this paper, we compose a trilogy of exploring the basic and generic supervision in the sequence from spatial, spatiotemporal and sequential perspectives. We materialize the supervisory signals through determining whether a pair of samples is from one frame or from on…
A number of deep learning based algorithms have been proposed to recover high-quality videos from low-quality compressed ones. Among them, some restore the missing details of each frame via exploring the spatiotemporal information of neighboring frames. However, these methods usually suffer from a narrow temporal scope, thus may miss some useful details from some frames outside the neighboring ones. In this paper, to boost artifact removal, on the one hand, we propose a Recursive Fusion (RF) module to model the temporal dependency within a long temporal range. Specifically, RF utilizes both th…
Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；University of Manitoba（曼尼托巴大学）
Recent self-supervised video representation learning methods have found significant success by exploring essential properties of videos, e.g. speed, temporal order, etc. This work exploits an essential yet under-explored property of videos, the video continuity, to obtain supervision signals for self-supervised representation learning. Specifically, we formulate three novel continuity-related pretext tasks, i.e. continuity justification, discontinuity localization, and missing section approximation, that jointly supervise a shared backbone for video representation learning. This self-supervisi…
Streaming perception is a critical task in autonomous driving that requires balancing the latency and accuracy of the autopilot system. However, current methods for streaming perception are limited as they only rely on the current and adjacent two frames to learn movement patterns. This restricts their ability to model complex scenes, often resulting in poor detection results. To address this limitation, we propose LongShortNet, a novel dual-path network that captures long-term temporal motion and integrates it with short-term spatial semantics for real-time perception. LongShortNet is notable…
Qingdao University（青岛大学）；Jiangxi University of Finance and Economics（江西财经大学）；Xidian University（西安电子科技大学）；Stony Brook University（石溪大学）
The current main stream methods formulate their video saliency mainly from two independent venues, i.e., the spatial and temporal branches. As a complementary component, the main task for the temporal branch is to intermittently focus the spatial branch on those regions with salient movements. In this way, even though the overall video saliency quality is heavily dependent on its spatial branch, however, the performance of the temporal branch still matter. Thus, the key factor to improve the overall video saliency is how to further boost the performance of these branches efficiently. In this p…
University at Buffalo（布法罗大学）；ETH Zürich（苏黎世联邦理工学院）；OPPO US Research Center（OPPO美国研究中心）；InnoPeak Tech（InnoPeak科技）；University of Tübingen（图宾根大学）
Visually exploring in a real-world 4D spatiotemporal space freely in VR has been a long-term quest. The task is especially appealing when only a few or even single RGB cameras are used for capturing the dynamic scene. To this end, we present an efficient framework capable of fast reconstruction, compact modeling, and streamable rendering. First, we propose to decompose the 4D spatiotemporal space according to temporal characteristics. Points in the 4D space are associated with probabilities of belonging to three categories: static, deforming, and new areas. Each area is represented and regular…
Department of Computer Science, University of Chinese Academy of Sciences（中国科学院大学计算机科学系）；Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS（中国科学院计算技术研究所中国科学院智能信息处理重点实验室）
Visual speech recognition is the task to decode the speech content from a video based on visual information, especially the movements of lips. It is also referenced as lipreading. Motivated by two problems existing in lipreading, words with similar pronunciation and the variation of word duration, we propose a novel 3D Feature Pyramid Attention (3D-FPA) module to jointly improve the representation power of features in both the spatial and temporal domains. Specifically, the input features are downsampled for 3 times in both the spatial and temporal dimensions to construct spatiotemporal featur…
Understanding crowd behavior in video is challenging for computer vision. There have been increasing attempts on modeling crowded scenes by introducing ever larger property ontologies (attributes) and annotating ever larger training datasets. However, in contrast to still images, manually annotating video attributes needs to consider spatiotemporal evolution which is inherently much harder and more costly. Critically, the most interesting crowd behaviors captured in surveillance videos (e.g., street fighting, flash mobs) are either rare, thus have few examples for model training, or unseen pre…
There is significant progress in recognizing traditional human activities from videos focusing on highly distinctive actions involving discriminative body movements, body-object and/or human-human interactions. Driver's activities are different since they are executed by the same subject with similar body parts movements, resulting in subtle changes. To address this, we propose a novel framework by exploiting the spatiotemporal attention to model the subtle changes. Our model is named Coarse Temporal Attention Network (CTA-Net), in which coarse temporal branches are introduced in a trainable g…
