Related papers: Short-Window Sliding Learning for Real-Time Violen…
Scene coordinate regression achieves impressive results in outdoor LiDAR localization but requires days of training. Since training needs to be repeated for each new scene, long training times make these methods impractical for…
This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory…
Violence descriptions in literature offer valuable insights for a wide range of research in the humanities. For historians, depictions of violence are of special interest for analyzing the societal dynamics surrounding large wars and…
This paper presents an investigation into machine learning techniques for violence detection in videos and their adaptation to a federated learning context. The study includes experiments with spatio-temporal features extracted from…
We propose general visual inspection model using Vision-Language Model~(VLM) with few-shot images of non-defective or defective products, along with explanatory texts that serve as inspection criteria. Although existing VLM exhibit high…
Reliable prediction by classifiers is crucial for their deployment in high security and dynamically changing situations. However, modern neural networks often exhibit overconfidence for misclassified predictions, highlighting the need for…
Learning to recognize actions from only a handful of labeled videos is a challenging problem due to the scarcity of tediously collected activity labels. We approach this problem by learning a two-pathway temporal contrastive model using…
Vision-language models (VLMs) can learn high-quality representations from a large-scale training dataset of image-text pairs. Prompt learning is a popular approach to fine-tuning VLM to adapt them to downstream tasks. Despite the satisfying…
We present a novel dataset aimed at advancing danger analysis and assessment by addressing the challenge of quantifying danger in video content and identifying how human-like a Large Language Model (LLM) evaluator is for the same. This is…
The Big Video Data generated in today's smart cities has raised concerns from its purposeful usage perspective, where surveillance cameras, among many others are the most prominent resources to contribute to the huge volumes of data, making…
Video Large Language Models (Video-LLMs) excel in video understanding but suffer from high inference latency during autoregressive generation. Speculative Decoding (SD) mitigates this by applying a draft-and-verify paradigm, yet existing…
Despite the recent advances in video classification, progress in spatio-temporal action recognition has lagged behind. A major contributing factor has been the prohibitive cost of annotating videos frame-by-frame. In this paper, we present…
How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact…
Deep learning models for autonomous driving, encompassing perception, planning, and control, depend on vast datasets to achieve their high performance. However, their generalization often suffers due to domain-specific data distributions,…
The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in high-quality image-text datasets for fine-tuning image…
Large Vision-Language Models (LVLMs) can be vulnerable to adversarial images that subtly bias their outputs toward plausible yet incorrect responses. We introduce a general, efficient, and training-free defense that combines image…
For training a video-based action recognition model that accepts multi-view video, annotating frame-level labels is tedious and difficult. However, it is relatively easy to annotate sequence-level labels. This kind of coarse annotations are…
Modern image classification is based upon directly predicting classes via large discriminative networks, which do not directly contain information about the intuitive visual features that may constitute a classification decision. Recently,…
Laboratories are prone to severe injuries from minor unsafe actions, yet continuous safety monitoring -- beyond mandatory pre-lab safety training -- is limited by human availability. Vision language models (VLMs) offer promise for…
Video classification has advanced tremendously over the recent years. A large part of the improvements in video classification had to do with the work done by the image classification community and the use of deep convolutional networks…