With only bounding-box annotations in the spatial domain, existing video scene text detection (VSTD) benchmarks lack temporal relation of text instances among video frames, which hinders the development of video text-related applications. In this paper, we systematically introduce a new large-scale benchmark, named as STVText4, a well-designed spatial-temporal detection metric (STDM), and a novel clustering-based baseline method, referred to as Temporal Clustering (TC). STVText4 opens a challenging yet promising direction of VSTD, termed as ST-VSTD, which targets at simultaneously detecting video scene texts in both spatial and temporal domains. STVText4 contains more than 1.4 million text instances from 161,347 video frames of 106 videos, where each instance is annotated with not only spatial bounding box and temporal range but also four intrinsic attributes, including legibility, density, scale, and lifecycle, to facilitate the community. With continuous propagation of identical texts in the video sequence, TC can accurately output the spatial quadrilateral and temporal range of the texts, which sets a strong baseline for ST-VSTD. Experiments demonstrate the efficacy of our method and the great academic and practical value of the STVText4. The dataset and code will be available soon.
In domain generalization, the knowledge learnt from one or multiple source domains is transferred to an unseen target domain. In this work, we propose a novel domain generalization approach for fine-grained scene recognition. We first propose a semantic scene descriptor that jointly captures the subtle differences between fine-grained scenes, while being robust to varying object configurations across domains. We model the occurrence patterns of objects in scenes, capturing the informativeness and discriminability of each object for each scene. We then transform such occurrences into scene prob…
T-STAR: A Large-Scale Benchmark for Spatio-Temporal Panoptic Scene Graph Generation in Satellite Video
School of Remote Sensing and Information Engineering, Wuhan University（武汉大学遥感信息工程学院）；School of Automation and Intelligent Sensing, Shanghai Jiao Tong University（上海交通大学自动化与智能感知学院）
Stanford University（斯坦福大学）；Toyota Research Institute（丰田研究院）
Video captioning is a challenging task that requires a deep understanding of visual scenes. State-of-the-art methods generate captions using either scene-level or object-level information but without explicitly modeling object interactions. Thus, they often fail to make visually grounded predictions, and are sensitive to spurious correlations. In this paper, we propose a novel spatio-temporal graph model for video captioning that exploits object interactions in space and time. Our model builds interpretable links and is able to provide explicit visual grounding. To avoid unstable performance c…
Hunan University（湖南大学）；Technische Universität Berlin（柏林工业大学）；Einstein Center Digital Future（爱因斯坦数字未来中心）；Hong Kong University of Science and Technology（香港科技大学）
Identifying independently moving objects is an essential task for dynamic scene understanding. However, traditional cameras used in dynamic scenes may suffer from motion blur or exposure artifacts due to their sampling principle. By contrast, event-based cameras are novel bio-inspired sensors that offer advantages to overcome such limitations. They report pixelwise intensity changes asynchronously, which enables them to acquire visual information at exactly the same rate as the scene dynamics. We develop a method to identify independently moving objects acquired with an event-based camera, i.e…
University of British Columbia（不列颠哥伦比亚大学）；Borealis AI；Vector Institute for AI（Vector AI研究所）
Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a novel spatio-temporal iterative inference framework that is powerful enough to jointly model complex multi-object representations and explicit temporal dependencies between latent variables across frames. This is achieved by leveraging 2D-LSTM, temporally conditioned inference and generation within the iterative amortized inference for posterior refinement. Our…
NeuroLip: An Event-driven Spatiotemporal Learning Framework for Cross-Scene Lip-Motion-based Visual Speaker Recognition
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）科学与工程学院）；Faculty of Electrical Engineering and Computing University of Zagreb（Zagreb大学电气工程与计算学院）；Faculty of Science, Radboud University（Radboud大学科学学院）
Scene model construction based on image rendering is an indispensable but challenging technique in computer vision and intelligent transportation systems. In this paper, we propose a framework for constructing 3D corridor-based road scene models. This consists of two successive stages: road detection and scene construction. The road detection is realized by a new superpixel Markov random field (MRF) algorithm. The data fidelity term in the MRF's energy function is jointly computed according to the superpixel features of color, texture and location. The smoothness term is established on the bas…
Action recognition has typically treated actions and activities as monolithic events that occur in videos. However, there is evidence from Cognitive Science and Neuroscience that people actively encode activities into consistent hierarchical part structures. However in Computer Vision, few explorations on representations encoding event partonomies have been made. Inspired by evidence that the prototypical unit of an event is an action-object interaction, we introduce Action Genome, a representation that decomposes actions into spatio-temporal scene graphs. Action Genome captures changes betwee…
Singapore University of Technology and Design（新加坡科技设计大学）；Adobe Research（Adobe研究院）
Video scene graph generation (VidSGG) aims to parse the video content into scene graphs, which involves modeling the spatio-temporal contextual information in the video. However, due to the long-tailed training data in datasets, the generalization performance of existing VidSGG models can be affected by the spatio-temporal conditional bias problem. In this work, from the perspective of meta-learning, we propose a novel Meta Video Scene Graph Generation (MVSGG) framework to address such a bias problem. Specifically, to handle various types of spatio-temporal conditional biases, our framework fi…
The waterdrops on windshields during driving can cause severe visual obstructions, which may lead to car accidents. Meanwhile, the waterdrops can also degrade the performance of a computer vision system in autonomous driving. To address these issues, we propose an attention-based framework that fuses the spatio-temporal representations from multiple frames to restore visual information occluded by waterdrops. Due to the lack of training data for video waterdrop removal, we propose a large-scale synthetic dataset with simulated waterdrops in complex driving scenes on rainy days. To improve the …
This paper presents a basic enhancement to the DeSTIN deep learning architecture by replacing the explicitly calculated transition tables that are used to capture temporal features with a simpler, more scalable mechanism. This mechanism uses feedback of state information to cluster over a space comprised of both the spatial input and the current state. The resulting architecture achieves state-of-the-art results on the MNIST classification benchmark.
4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation
National Key Lab of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（多谱信息智能处理国家实验室，人工智能与自动化学院，华中科技大学）；School of Computing, National University of Singapore（计算学院，新加坡国立大学）
Real-Time Spatio-Temporal Reconstruction of Dynamic Endoscopic Scenes with 4D Gaussian Splatting
University of Liverpool, Liverpool, UK（利物浦大学）；Xi'an Jiaotong-Liverpool University, Suzhou, China（西安交通大学利物浦大学）；University of Cambridge, Cambridge, UK（剑桥大学）
Nanjing University of Science and Technology（南京理工大学）
Anomaly identification is highly dependent on the relationship between the object and the scene, as different/same object actions in same/different scenes may lead to various degrees of normality and anomaly. Therefore, object-scene relation actually plays a crucial role in anomaly detection but is inadequately explored in previous works. In this paper, we propose a Spatial-Temporal Relation Learning (STRL) framework to tackle the video anomaly detection task. First, considering dynamic characteristics of the objects as well as scene areas, we construct a Spatio-Temporal Auto-Encoder (STAE) to…
Light emitted from a source into a scene can undergo complex interactions with scene surfaces of different material types before being reflected. During this transport, every surface reflection is encoded in the properties of the photons that reach the detector, including time, direction, intensity, wavelength and polarization. Conventional imaging systems capture intensity by integrating over all other dimensions of the light, hiding this rich scene information. Existing methods are capable of untangling these measurements into their spatial and temporal dimensions, fueling geometric scene un…
Structure from motion (SfM) enables us to reconstruct a scene via casual capture from cameras at different viewpoints, and novel view synthesis (NVS) allows us to render a captured scene from a new viewpoint. Both are hard with casual capture and dynamic scenes: SfM produces noisy and spatio-temporally sparse reconstructed point clouds, resulting in NVS with spatio-temporally inconsistent effects. We consider SfM and NVS parts together to ease the challenge. First, for SfM, we recover stable camera poses, then we defer the requirement for temporally-consistent points across the scene and recon…
Assigning consistent temporal identifiers to multiple moving objects in a video sequence is a challenging problem. A solution to that problem would have immediate ramifications in multiple object tracking and segmentation problems. We propose a strategy that treats the temporal identification task as a spatio-temporal clustering problem. We propose an unsupervised learning approach using a convolutional and fully connected autoencoder, which we call deep heterogeneous autoencoder, to learn discriminative features from segmentation masks and detection bounding boxes. We extract masks and their …
In autonomous vehicles (AVs), early warning systems rely on collision prediction to ensure occupant safety. However, state-of-the-art methods using deep convolutional networks either fail at modeling collisions or are too expensive/slow, making them less suitable for deployment on AV edge hardware. To address these limitations, we propose sg2vec, a spatio-temporal scene-graph embedding methodology that uses Graph Neural Network (GNN) and Long Short-Term Memory (LSTM) layers to predict future collisions via visual scene perception. We demonstrate that sg2vec predicts collisions 8.11% more accur…
Spatio-Temporal Data Enhanced Vision-Language Model for Traffic Scene Understanding
School of Computer Science and Engineering, and the MOE Engineering Research Center of Advanced Computer Application Technology, Beihang University（计算机科学与工程学院，以及教育部先进计算机应用技术工程研究中心，北京航空航天大学）；School of Computer Science and Engineering, the School of Economics and Management, and the MIIT Key Laboratory of Data Intelligence and Management, Beihang University（计算机科学与工程学院，经济管理学院，以及工信部数据智能与管理重点实验室，北京航空航天大学）；Gaoling School of Artificial Intelligence, Renmin University of China（中关村人工智能学院，中国人民大学）；DiDi Global Inc.（滴滴出行公司）
Shanghai Jiao Tong University（上海交通大学）；The Chinese University of Hong Kong（香港中文大学）
Contrastive learning has shown promising potential in self-supervised spatio-temporal representation learning. Most works naively sample different clips to construct positive and negative pairs. However, we observe that this formulation inclines the model towards the background scene bias. The underlying reasons are twofold. First, the scene difference is usually more noticeable and easier to discriminate than the motion difference. Second, the clips sampled from the same video often share similar backgrounds but have distinct motions. Simply regarding them as positive pairs will draw the mode…
STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering
Institute of Computing Technology, Chinese Academy of Sciences, ICT（中国科学院计算技术研究所）；University of Chinese Academy of Sciences, UCAS（中国科学院大学）；The University of Queensland（昆士兰大学）；University of California, Merced（加州大学梅尔塞德斯分校）
Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）
A novel framework named Markov Clustering Network (MCN) is proposed for fast and robust scene text detection. MCN predicts instance-level bounding boxes by firstly converting an image into a Stochastic Flow Graph (SFG) and then performing Markov Clustering on this graph. Our method can detect text objects with arbitrary size and orientation without prior knowledge of object size. The stochastic flow graph encode objects' local correlation and semantic information. An object is modeled as strongly connected nodes, which allows flexible bottom-up detection for scale-varying and rotated objects. …
We propose SF2SE3, a novel approach to estimate scene dynamics in form of a segmentation into independently moving rigid objects and their SE(3)-motions. SF2SE3 operates on two consecutive stereo or RGB-D images. First, noisy scene flow is obtained by application of existing optical flow and depth estimation algorithms. SF2SE3 then iteratively (1) samples pixel sets to compute SE(3)-motion proposals, and (2) selects the best SE(3)-motion proposal with respect to a maximum coverage formulation. Finally, objects are formed by assigning pixels uniquely to the selected SE(3)-motions based on consi…
Beijing University of Posts and Telecommunications（北京邮电大学）
Exemplar-based video colorization is an essential technique for applications like old movie restoration. Although recent methods perform well in still scenes or scenes with regular movement, they always lack robustness in moving scenes due to their weak ability in modeling long-term dependency both spatially and temporally, leading to color fading, color discontinuity or other artifacts. To solve this problem, we propose an exemplar-based video colorization framework with long-term spatiotemporal dependency. To enhance the long-term spatial dependency, a parallelized CNN-Transformer block and …
Lane detection is one of the indispensable and key elements of self-driving environmental perception. Many lane detection models have been proposed, solving lane detection under challenging conditions, including intersection merging and splitting, curves, boundaries, occlusions and combinations of scene types. Nevertheless, lane detection will remain an open problem for some time to come. The ability to cope well with those challenging scenes impacts greatly the applications of lane detection on advanced driver assistance systems (ADASs). In this paper, a spatio-temporal network with double Co…
University of Science and Technology of China（中国科学技术大学）；Ping An Technology Co., Ltd（平安科技有限公司）；Hefei ZhanDa Intelligence Technology Co., Ltd（合肥展大智能科技有限公司）
Multi-modal aerial view object classification (MAVOC) in Automatic target recognition (ATR), although an important and challenging problem, has been under studied. This paper firstly finds that fine-grained data, class imbalance and various shooting conditions preclude the representational ability of general image classification. Moreover, the MAVOC dataset has scene aggregation characteristics. By exploiting these properties, we propose Scene Clustering Based Pseudo-labeling Strategy (SCP-Label), a simple yet effective method to employ in post-processing. The SCP-Label brings greater accuracy…
University of California, San Diego（加州大学圣迭戈分校）；University of Sao Paulo（圣保罗大学）
Forecasting long-term human motion is a challenging task due to the non-linearity, multi-modality and inherent uncertainty in future trajectories. The underlying scene and past motion of agents can provide useful cues to predict their future motion. However, the heterogeneity of the two inputs poses a challenge for learning a joint representation of the scene and past trajectories. To address this challenge, we propose a model based on grid representations to forecast agent trajectories. We represent the past trajectories of agents using binary 2-D grids, and the underlying scene as a RGB bird…
Enhancing Multi-Camera People Tracking with Anchor-Guided Clustering and Spatio-Temporal Consistency ID Re-Assignment
University of Washington（华盛顿大学）；Electronics and Telecommunications Research Institute（电子与电信研究所）；National Center for High-Performance Computing（国家高性能计算中心）
提出一种结合锚定引导聚类与时空一致性的多摄像机多人员跟踪方法，在CVPR AI City Challenge 2023上以95.36% IDF1获第一名。
Tianjin University（天津大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）
Shadow removal in a single image has received increasing attention in recent years. However, removing shadows over dynamic scenes remains largely under-explored. In this paper, we propose the first data-driven video shadow removal model, termed PSTNet, by exploiting three essential characteristics of video shadows, i.e., physical property, spatio relation, and temporal coherence. Specifically, a dedicated physical branch was established to conduct local illumination estimation, which is more applicable for scenes with complex lighting and textures, and then enhance the physical features via a …
Istituto Sistemi Complessi, Consiglio Nazionale delle Ricerche（意大利国家研究委员会复杂系统研究所）
The interest in 3D dynamical tracking is growing in fields such as robotics, biology and fluid dynamics. Recently, a major source of progress in 3D tracking has been the study of collective behaviour in biological systems, where the trajectories of individual animals moving within large and dense groups need to be reconstructed to understand the behavioural interaction rules. Experimental data in this field are generally noisy and at low spatial resolution, so that individuals appear as small featureless objects and trajectories must be retrieved by making use of epipolar information only. Mor…
Purdue University（普渡大学）；University of Hawaii Cancer Center（夏威夷大学癌症中心）；Curtin University（科廷大学）
It is well known that dietary habits have a significant influence on health. While many studies have been conducted to understand this relationship, little is known about the relationship between eating environments and health. Yet researchers and health agencies around the world have recognized the eating environment as a promising context for improving diet and health. In this paper, we propose an image clustering method to automatically extract the eating environments from eating occasion images captured during a community dwelling dietary study. Specifically, we are interested in learning …
Research in action detection has grown in the recentyears, as it plays a key role in video understanding. Modelling the interactions (either spatial or temporal) between actors and their context has proven to be essential for this task. While recent works use spatial features with aggregated temporal information, this work proposes to use non-aggregated temporal information. This is done by adding an attention based method that leverages spatio-temporal interactions between elements in the scene along the clip.The main contribution of this work is the introduction of two cross attention blocks…
