For video anomaly detection, it's both important to detect when the event happens and what the event is. The tasks of temporal grounding and semantic understanding can benefit from joint learning, but no existing work support it. To address this problem, we introduce VAGU (Video Anomaly Grounding and Understanding), the first benchmark designed to jointly evaluate semantic understanding and precise temporal grounding of anomalies, with comprehensive annotations and objective multiple-choice Video QA. Besides, we propose Glance then Scrutinize (GtS), the first training-free framework that achieves the best balance performance in both accuracy and efficiency. GtS uniquely balances high temporal precision and semantic interpretability while meeting practical speed requirements, outperforming previous methods in real-world scenarios. Furthermore, we introduce the JeAUG metric for holistic evaluation of both speed and accuracy. Extensive experiments demonstrate the superior effectiveness and practicality of our benchmark, framework, and metric.

Counterfactual Regret Minimization is the state-of-the-art algorithm for solving imperfect information games, yet it struggles against scalability. While existing pruning techniques primarily focus on pruning unreachable branches, they fail to account for subgames in which strategies have temporarily converged. Continuing to update strategies within these subgames leads to unnecessary computational overhead. To address this, we propose Subgame Pruning, a novel regret-based pruning paradigm that accelerates traversal of the public tree by dynamically pruning subgames where strategies remain stable across iterations. To ensure safe and efficient pruning, we introduce two key mechanisms: Pruning Constraint Checking, which verifies whether a subgame satisfies pruning criteria, and Regret Matching Compensation, which defers regret matching and average strategy updates until the pruned subgames are revisited. Our method significantly reduces computational overhead while preserving the theoretical convergence guarantees of CFR. In particular, the exploitability of the average strategy profile remains bounded by$\mathcal {O}(1/\sqrt{T})$. Experimental results across five benchmark games demonstrate substantial reductions in the number of traversed nodes, with exploitability comparable to that of standard CFR.

Video anomaly detection (VAD) aims at detecting anomalous events in videos. Most existing VAD methods distinguish anomalies by learning visual features of the video, which usually face several challenges in real-world applications. First, these methods are mostly scene-dependent, whose performances degrade obviously once the scene changes. Second, these methods are incapable of giving explanations to the detected anomalies. Third, these methods cannot adjust definitions of normal or abnormal events during test time without retraining the model. One important reason for the drawbacks is that these visual-based methods mainly detect anomalies by fitting visual patterns rather than semantically understanding the events in videos. In this paper, we propose a training-free method named Semantic Understanding based Video Anomaly Detection (SUVAD) using multi-modal large language model (MLLM). By exploiting MLLMs to generate detailed texture descriptions for videos, SUVAD achieves semantic video understanding, and then detects anomalies directly by large language models. We also designed several techniques to mitigate the hallucination problem of MLLMs. Compared to the methods based on visual features, SUVAD obtains obviously better scene generalization, anomaly interpretability, and the ability of flexible adjustment of anomaly definitions. We evaluate our method on five mainstream datasets. The results show that SUVAD achieves the best performance among all the training-free methods.

Semi-supervised video anomaly detection (SVAD) is a challenging computer vision task due to the diversity, randomness, and rarity of abnormal events in videos. A series of important SVAD methods follow the frame prediction strategy, where the model is trained only on normal videos and thus frames with higher prediction error are regarded as anomalies. However, these methods often suffer from inadequate sensitivity to anomalies because the prediction error of anomalous frames is insufficiently distinguishable from the error of normal frames. In this paper, we propose a compact deformable 3D convolution (CD3D) for feature extraction in SVAD models, which effectively enhances the discriminating ability between normal and anomalous frames. In CD3D, the offsets of sampling locations are predicted by applying a set of extra separable 3D convolutions to multiple frames, so that the context information is better utilized with reduced computational costs. Our proposed method achieves the best performance among the methods without resorting to additional supervised information. It can also be conveniently applied to methods that utilize extra supervised information, which further enhances their performances.

With the popularity of digital cameras and smart-phones, capturing document images of physical documents for electronic storage has become popular, but the captured document images suffer various deformations. Document image rectification has been studied intensively, but existing methods do not perform sufficiently for document images captured in complex scenes due to the various environmental factors. In this paper, we propose an end-to-end rectification model by stacking 3D and 2D Siamese networks. Three regularization terms are used to enforce 3D reconstruction consistency and 2D texture consistency, respectively. Experimental results on real world datasets demonstrate that the three regularization terms with Siamese networks can significantly improve the rectification performance, and our method performs superiorly compared to state-of-the-art methods.

The success of deep neural networks usually relies on a large number of labeled training samples, which unfortunately are not easy to obtain in practice. Unsupervised domain adaptation focuses on the problem where there is no labeled data in the target domain. In this paper, we propose a novel deep unsupervised domain adaptation method that learns transferable features. Different from most existing methods, it attempts to learn a better domain-invariant feature representation by performing a category-wise adaptation to match the conditional distributions of samples with respect to each category. A self-paced learning strategy is used to bring the awareness of label information gradually, which makes the category-wise adaptation feasible even if the labels are unavailable in target domain. Then, we give detailed theoretical analysis to explain how the better performance is obtained. The experimental results show that our method outperforms the current state of the arts on standard domain adaptation datasets.

In this paper, we are devoted to solving the problem of crossing surveillance and mobile phone visual location recognition, especially for the case that the query and reference images are captured by mobile phone and surveillance camera, respectively. Besides, we also study the influence of the environmental condition variations on this problem. To explore that problem, we first build a cross-device location recognition dataset, which includes images of 22 locations taken by mobile phones and surveillance cameras under different time and weather conditions. Then based on careful analysis of the problems existing in the data, we specifically design a method which unifies an unsupervised subspace alignment method and the semi-supervised Laplacian support vector machine. Experiments are performed on our dataset. Compared with several related methods, our method shows to be more efficient on the problem of crossing surveillance and mobile phone visual location recognition. Furthermore, the influence of several factors such as feature, time, and weather is studied.

For spectral embedding/clustering, it is still an open problem on how to construct an relation graph to reflect the intrinsic structures in data. In this paper, we proposed an approach, named Relation Discovery based Slow Feature Analysis (ReD-SFA), for feature learning and graph construction simultaneously. Given an initial graph with only a few nearest but most reliable pairwise relations, new reliable relations are discovered by an assumption of reliability preservation, i.e., the reliable relations will preserve their reliabilities in the learnt projection subspace. We formulate the idea as a cross entropy (CE) minimization problem to reduce the discrepancy between two Bernoulli distributions parameterized by the updated distances and the existing relation graph respectively. Furthermore, to overcome the imbalanced distribution of samples, a Boosting-like strategy is proposed to balance the discovered relations over all clusters. To evaluate the proposed method, extensive experiments are performed with various trajectory clustering tasks, including motion segmentation, time series clustering and crowd detection. The results demonstrate that ReDSFA can discover reliable intra-cluster relations with high precision, and competitive clustering performance can be achieved in comparison with state-of-the-art.

In this paper, we focus on the problem of cross-domain object recognition [4], which has long been one of the challenging problems in computer vision. This problem typically arises when training (source domain) and test (target domain) samples are drawn from different distributions. In the problem of object recognition, this case is usually caused by the situation that training and test samples are acquired under different sets of background, lighting, view point, resolution conditions, etc. One popular solution to the problem of cross-domain object recognition is minimizing the difference between the source and target distributions. Existing methods are devoted to minimizing that domain difference in a complex image space, which makes the problem hard to solve because of background influence, as shown in Figure 1 (a). Since the object and background are twisted in that image feature space, the discrepancy caused by background is difficult to eliminate, which makes it hard to learn optimal fS and fT for minimizing D( fS(XS), fT (XT )). To discount the influence of the background, we propose to minimize that difference using object alignment. As shown in Figure 1 (b), we minimize the domain difference by transferring to the feature space of aligned objects XS and XT , but not the image feature space having background influence. The key insight of our approach is that the difference between the source and target distributions can be reduced by discounting the influence from the ambiguous background. We define the semantic object as the object that occurs in all the images of one class. To discount the background influence, our primary goal is to automatically localize the semantic object so that the irrelevant background can be eliminated. Then based on the semantic object regions, we can learn an object detector that is robust to the influence of the irrelevant background and makes the crossdomain object recognition much easier than before. In addition, since our detectors are learned in a weakly supervised way, we utilize the classificaSource domain Selective search Object alignment — Topic discovery

Markov Random Field (MRF) is an important tool and has been widely used in many vision tasks. Thus, the optimization of MRFs is a problem of fundamental importance. Recently, Veskler and Kumar et. al propose the range move algorithms, which are one of the most successful solvers to this problem. However, two problems have limited the applicability of previous range move algorithms: 1) They are limited in the types of energies they can handle (i.e. only truncated convex functions); 2) These algorithms tend to be very slow compared to other graph-cut based algorithms (e.g. α-expansion and αβ-swap). In this paper, we propose a generalized range swap algorithm (GRSA) for efficient optimization of MRFs. To address the first problem, we extend the GRSA to arbitrary semimetric energies by restricting the chosen labels in each move so that the energy is submodular on the chosen subset. Furthermore, to feasibly choose the labels satisfying the submodular condition, we provide a sufficient condition of the submodularity. For the second problem, unlike previous range move algorithms which execute the set of all possible range moves, we dynamically obtain the iterative moves by solving a set cover problem, which greatly reduces the number of moves during the optimization. Experiments show that the GRSA offers a great speedup over previous range swap algorithms, while it obtains competitive solutions.

Common action recognition methods describe an action sequence along with its time axis, i.e., first extracting features from the x y plane, and then modeling the dynamic changes along with the time axis. Other than the ordinary x y plane-based representation, other views, e.g., xt slice-based representation, may be more efficient to distinguish different actions. In this paper, we investigate different slicing views of the spatiotemporal volume to organize action sequences and propose an efficient slice representation for human action recognition. First, a minimum average entropy principle is proposed to select the optimal slicing angle for each action sequence adaptively. This allows the foreground pixels to be distributed in the fewest slices so as to reduce more uncertainty caused by the information dispersed in different slices. Then, the obtained slice sequence is transformed into a pair of 1-D signals to describe the distribution of foreground pixels along the time axis. Finally, the mel frequency cepstrum coefficient features are calculated to describe the spectrum characteristics of the 1-D signals over time. Thus, a 3-D spatiotemporal action volume is efficiently transformed into a low-dimensional spectrum features. Extensive experiments on the 2-D human action data sets (the UIUC and the WEIZMANN) as well as the Microsoft Research (MSR) Action3-D depth data set demonstrate the effectiveness of the slice-based representation, where the recognition performance can reach to the state-of-the-art level with high efficiency.

The aim of this work is to localize a query mobile photograph by utilizing surveillance images, which naturally provide location information. We cast this cross-device visual localization problem as a classification task. By exploiting the surveillance network to collect reference images, the data acquisition process is significantly facilitated. However, the discrepancy between mobile images and surveillance images makes the training samples difficult to be used directly, and the scarcity of training samples caused by the immobility of surveillance cameras further degrades the performance. In contrast to most traditional domain adaptation problems and semi-supervised problems, the scarce labeled data and plentiful unlabeled data exist in different domains. Our location recognition method first exploits the unsupervised subspace alignment to weaken the discrepancy between the two domains, and then adopts the semi-supervised Laplacian SVM to reinforce the discriminant information utilizing the unlabeled mobile images. Experimental results show that our location recognition method significantly outperforms other related methods.

Object recognition, which consists of classification and detection, has two important attributes for robustness: (1) Closeness: detection windows should be close to object locations, and (2) Adaptiveness: object matching should be adaptive to object variations in classification. It is difficult to satisfy both attributes by considering classification and detection separately, thus recent studies combine them based on confidence contextualization and foreground modeling. However, these combinations neglect feature saliency and object structure, which are important for recognition. In fact, object recognition originates in the mechanism of "what" and "where" pathways in human visual systems, and more importantly, these pathways have feedback to each other, which provides a probable way to improve closeness and adaptiveness. Inspired by the feedback, we propose a robust object recognition framework by designing a computational model of the feedback mechanism. In the "what" feedback, the feature saliency from classification is exploited to rectify detection windows for better closeness, while in the "where" feedback, object parts from detection are used to model object matching of object structure for better adaptiveness. Experiments show that the "what" and "where" feedback can be effective to improve closeness and adaptiveness for robust object recognition, and encouraging results are obtained on the challenging PASCAL VOC 2007 dataset.

This letter considers the combination of multiple classification and clustering results to improve the prediction accuracy. First, an object-similarity graph is constructed from multiple clustering results. The labels predicted by the classification models are then propagated on this graph to adaptively satisfy the smoothness of the prediction over the graph. The convex learning problem is efficiently solved by the label propagation algorithm. A semi-supervised extension is also provided to further improve the performance. Experiments on 11 tasks identify the validity of the proposed models.