Related papers: Sparse Reasoning is Enough: Biological-Inspired Fr…

Video anomaly detection (VAD) holds immense importance across diverse domains such as surveillance, healthcare, and environmental monitoring. While numerous surveys focus on conventional VAD methods, they often lack depth in exploring…

We propose a novel dense mapping framework for sparse visual SLAM systems which leverages a compact scene representation. State-of-the-art sparse visual SLAM systems provide accurate and reliable estimates of the camera trajectory and…

Multi-modal reasoning requires the seamless integration of visual and linguistic cues, yet existing Chain-of-Thought methods suffer from two critical limitations in cross-modal scenarios: (1) over-reliance on single coarse-grained image…

Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textual representations often become intertwined in the deeper…

Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be…

While deep feature learning has revolutionized techniques for static-image understanding, the same does not quite hold for video processing. Architectures and optimization techniques used for video are largely based off those for static…

This paper proposes a novel deep learning framework for multi-modal motion prediction. The framework consists of three parts: recurrent neural networks to process the target agent's motion process, convolutional neural networks to process…

Accurately understanding and deciding high-level meta-actions is essential for ensuring reliable and safe autonomous driving systems. While vision-language models (VLMs) have shown significant potential in various autonomous driving tasks,…

While anomaly detection has made significant progress, generating detailed analyses that incorporate industrial knowledge remains a challenge. To address this gap, we introduce OmniAD, a novel framework that unifies anomaly detection and…

Learning a generative model from partial data (data with missingness) is a challenging area of machine learning research. We study a specific implementation of the Auto-Encoding Variational Bayes (AEVB) algorithm, named in this paper as a…

Humans detect real-world object anomalies by perceiving, interacting, and reasoning based on object-conditioned physical knowledge. The long-term goal of Industrial Anomaly Detection (IAD) is to enable machines to autonomously replicate…

Human-centric Video Anomaly Detection (VAD) aims to identify human behaviors that deviate from normal. At its core, human-centric VAD faces substantial challenges, such as the complexity of diverse human behaviors, the rarity of anomalies,…

Hypothesis. Artificial general intelligence is, at its core, a compression problem. Effective compression demands resonance: deep learning scales best when its architecture aligns with the fundamental structure of the data. These are the…

We propose a novel mechanism for real-time (human-in-the-loop) feedback focused on false positive reduction to enhance anomaly detection models. It was designed for the lightweight deployment of a behavioral network anomaly detection model.…

Existing video anomaly detection datasets are inadequate for representing complex anomalies that occur due to the interactions between objects. The absence of complex anomalies in previous video anomaly detection datasets affects research…

Anomalies are rare and anomaly detection is often therefore framed as One-Class Classification (OCC), i.e. trained solely on normalcy. Leading OCC techniques constrain the latent representations of normal motions to limited volumes and…

Video understanding requires not only visual recognition but also complex reasoning. While Vision-Language Models (VLMs) demonstrate impressive capabilities, they typically process videos largely in a single-pass manner with limited support…

Latent action models (LAMs) offer a promising path to pre-training embodied agents on large amounts of action-free video. They infer latent actions between consecutive observations that can later be decoded to ground-truth actions using a…

Reasoning segmentation increasingly employs reinforcement learning to generate explanatory reasoning chains that guide Multimodal Large Language Models. While these geometric rewards are primarily confined to guiding the final localization,…

Long video understanding is heavily bottlenecked by a rigid one-shot paradigm: existing methods either densely encode videos at prohibitive memory and latency costs, or aggressively compress them into sparse frame sets that irreversibly…