Zero-Shot Anomaly Detection (ZSAD) is an emerging AD paradigm. Unlike the traditional unsupervised AD setting that requires a large number of normal samples to train a model, ZSAD is more practical for handling data-restricted real-world scenarios. Recently, Multimodal Large Language Models (MLLMs) have shown revolutionary reasoning capabilities in various vision tasks. However, the reasoning of image abnormalities remains underexplored due to the lack of corresponding datasets and benchmarks. To facilitate research in AD & reasoning, we establish the first visual instruction tuning dataset, Anomaly-Instruct-125k, and the evaluation benchmark, VisA-D&R. Through investigation with our benchmark, we reveal that current MLLMs like GPT-4o cannot accurately detect and describe fine-grained anomalous details in images. To address this, we propose Anomaly-OneVision (Anomaly-OV), the first specialist visual assistant for ZSAD and reasoning. Inspired by human behavior in visual inspection, Anomaly-OV leverages a Look-Twice Feature Matching (LTFM) mechanism to adaptively select and emphasize abnormal visual tokens. Extensive experiments demonstrate that Anomaly-OV achieves significant improvements over advanced generalist models in both detection and reasoning. Extensions to medical and 3D AD are provided for future study. The link to our project page: https://xujiacong.github.io/Anomaly-OV/

Vision-language models (VLMs) are capable of recognizing unseen actions. However, existing VLMs lack intrinsic understanding of procedural action concepts. Hence, they overfit to fixed labels and are not invariant to unseen action synonyms. To address this, we propose a simple fine-tuning technique, Action Concept Enhancement (ACE), to improve the robustness and concept understanding of VLMs in procedural action classification. ACE continually incorporates augmented action synonyms and negatives in an auxiliary classification loss by stochastically replacing fixed labels during training. This creates new combinations of action labels over the course of fine-tuning and prevents overfitting to fixed action representations. We show the enhanced concept understanding of our VLM, by visualizing the alignment of encoded embeddings of unseen action synonyms in the embedding space. Our experiments on the ATA, IKEA and GTEA datasets demonstrate the efficacy of ACE in domains of cooking and assembly leading to significant improvements in zero-shot action classification while maintaining competitive performance on seen actions.

We present a novel method for weakly-supervised action segmentation and unseen error detection in anomalous instructional videos. In the absence of an appropriate dataset for this task, we introduce the Anomalous Toy Assembly (ATA) dataset1, which comprises 1152 untrimmed videos of 32 participants assembling three different toys, recorded from four different viewpoints. The training set comprises 27 participants who assemble toys in an expected and consistent manner, while the test and validation sets comprise 5 participants who display sequential anomalies in their task. We introduce a weakly labeled segmentation algorithm that is a generalization of the constrained Viterbi algorithm and identifies potential anomalous moments based on the difference between future anticipation and current recognition results. The proposed method is not restricted by the training transcripts during testing, allowing for the inference of anomalous action sequences while maintaining real-time performance. Based on these segmentation results, we also introduce a baseline to detect pre-defined human errors, and benchmark results on the ATA dataset. Experiments were conducted on the ATA and CSV datasets, outperforming the state-of-the-art in segmenting anomalous videos under both online and offline conditions.

Considering the functionality of situational awareness in safety-critical automation systems, the perception of risk in driving scenes and its explainability is of particular importance for autonomous and cooperative driving. Toward this goal, this paper proposes a new research direction of joint risk localization in driving scenes and its risk explanation as a natural language description. Due to the lack of standard benchmarks, we collected a large-scale dataset, DRAMA (Driving Risk Assessment Mechanism with A captioning module), which consists of 17,785 interactive driving scenarios collected in Tokyo, Japan. Our DRAMA dataset accommodates video- and object-level questions on driving risks with associated important objects to achieve the goal of visual captioning as a free-form language description utilizing closed and open-ended responses for multi-level questions, which can be used to evaluate a range of visual captioning capabilities in driving scenarios. We make this data available to the community for further re-search. Using DRAMA, we explore multiple facets of joint risk localization and captioning in interactive driving scenarios. In particular, we benchmark various multi-task pre-diction architectures and provide a detailed analysis of joint risk localization and risk captioning. The data set is available at https://usa.honda-ri.com/drama

This paper addresses a new problem of weakly-supervised online action segmentation in instructional videos. We present a framework to segment streaming videos online at test time using Dynamic Programming and show its advantages over greedy sliding window approach. We improve our framework by introducing the Online-Offline Discrepancy Loss (OODL) to encourage the segmentation results to have a higher temporal consistency. Furthermore, only during training, we exploit framewise correspondence between multiple views as supervision for training weakly-labeled instructional videos. In particular, we investigate three different multi-view inference techniques to generate more accurate frame-wise pseudo ground-truth with no additional annotation cost. We present results and ablation studies on two benchmark multi-view datasets, Breakfast and IKEA ASM. Experimental results show efficacy of the proposed methods both qualitatively and quantitatively in two domains of cooking and assembly.

We propose a robust solution to future trajectory forecast, which can be practically applicable to autonomous agents in highly crowded environments. For this, three aspects are particularly addressed in this paper. First, we use composite fields to predict future locations of all road agents in a singleshot, which results in a constant time complexity, regardless of the number of agents in the scene. Second, interactions between agents are modeled as a non-local response, enabling spatial relationships between different locations to be captured temporally as well (i.e., in spatio-temporal interactions). Third, the semantic context of the scene are modeled and take into account the environmental constraints that potentially influence the future motion. To this end, we validate the robustness of the proposed approach using the ETH, UCY, and SDD datasets and highlight its practical functionality compared to the current state-of-the-art methods.

This paper examines the problem of dynamic traffic scene classification under space-time variations in viewpoint that arise from video captured on-board a moving vehicle. Solutions to this problem are important for realization of effective driving assistance technologies required to interpret or predict road user behavior. Currently, dynamic traffic scene classification has not been adequately addressed due to a lack of benchmark datasets that consider spatiotemporal evolution of traffic scenes resulting from a vehicle's ego-motion. This paper has three main contributions. First, an annotated dataset is released to enable dynamic scene classification that includes 80 hours of diverse high quality driving video data clips collected in the San Francisco Bay area. The dataset includes temporal annotations for road places, road types, weather, and road surface conditions. Second, we introduce novel and baseline algorithms that utilize semantic context and temporal nature of the dataset for dynamic classification of road scenes. Finally, we showcase algorithms and experimental results that highlight how extracted features from scene classification serve as strong priors and help with tactical driver behavior understanding. The results show significant improvement from previously reported driving behavior detection baselines in the literature.

The ability to semantically interpret hand-drawn line sketches, although very challenging, can pave way for novel applications in multimedia. We propose SKETCHPARSE, the first deep-network architecture for fully automatic parsing of freehand object sketches. SKETCHPARSE is configured as a two-level fully convolutional network. The first level contains shared layers common to all object categories. The second level contains a number of expert sub-networks. Each expert specializes in parsing sketches from object categories which contain structurally similar parts. Effectively, the two-level configuration enables our architecture to scale up efficiently as additional categories are added. We introduce a router layer which (i) relays sketch features from shared layers to the correct expert (ii) eliminates the need to manually specify object category during inference. To bypass laborious part-level annotation, we sketchify photos from semantic object-part image datasets and use them for training. Our architecture also incorporates object pose prediction as a novel auxiliary task which boosts overall performance while providing supplementary information regarding the sketch. We demonstrate SKETCHPARSE's abilities (i) on two challenging large-scale sketch datasets (ii) in parsing unseen, semantically related object categories (iii) in improving fine-grained sketch-based image retrieval. As a novel application, we also outline how SKETCHPARSE's output can be used to generate caption-style descriptions for hand-drawn sketches.

In this paper, we present a novel scheme for text-independent online writer identification. As a first contribution, we propose histogram based features, inspired from the area of object detection, to describe the structural primitives of handwriting. Secondly, we have used sparse coding techniques to learn prototypes, that describe the general writing characteristics of the authors. To the best of our knowledge, the present proposal is the first of its kind that exploits the sparse learning framework for online writer identification. In addition, we consider the inclusion of ideas from information retrieval into our sparse representation to formulate a novel descriptor for each document. The efficacy of our proposal is tested on the handwritten paragraphs and text lines of the IAM On-Line Handwriting Database. We also provide a quantitative comparison of performance of our histogram based features with Fourier and Wavelet descriptors. The results are promising.