Related papers: LaneTCA: Enhancing Video Lane Detection with Tempo…
Video-based person re-identification (ReID) is challenging due to the presence of various interferences in video frames. Recent approaches handle this problem using temporal aggregation strategies. In this work, we propose a novel Context…
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos. The temporal relation is complex in those datasets, including challenges like composite action, and co-occurring action.…
Effectively constructing context information with long-term dependencies from video sequences is crucial for object tracking. However, the context length constructed by existing work is limited, only considering object information from…
We present Scene-Graph Based Multi-Modal Traffic Agent (SGTA), a modular framework for traffic video understanding that combines structured scene graphs with multi-modal reasoning. It constructs a traffic scene graph from roadside videos…
Anticipation of accidents ahead of time in autonomous and non-autonomous vehicles aids in accident avoidance. In order to recognize abnormal events such as traffic accidents in a video sequence, it is important that the network takes into…
The monocular depth estimation task has recently revealed encouraging prospects, especially for the autonomous driving task. To tackle the ill-posed problem of 3D geometric reasoning from 2D monocular images, multi-frame monocular methods…
In this paper, we place the atomic action detection problem into a Long-Short Term Context (LSTC) to analyze how the temporal reliance among video signals affect the action detection results. To do this, we decompose the action recognition…
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.…
Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately:…
Traffic Management Centers (TMCs) routinely use traffic cameras to provide situational awareness regarding traffic, road, and weather conditions. Camera footage is quite useful for a variety of diagnostic purposes; yet, most footage is kept…
There is significant progress in recognizing traditional human activities from videos focusing on highly distinctive actions involving discriminative body movements, body-object and/or human-human interactions. Driver's activities are…
In the world of action recognition research, one primary focus has been on how to construct and train networks to model the spatial-temporal volume of an input video. These methods typically uniformly sample a segment of an input clip…
Autonomous driving requires a structured understanding of the surrounding road network to navigate. One of the most common and useful representation of such an understanding is done in the form of BEV lane graphs. In this work, we use the…
Temporal action detection aims to locate the boundaries of action in the video. The current method based on boundary matching enumerates and calculates all possible boundary matchings to generate proposals. However, these methods neglect…
Lane graph estimation is an essential and highly challenging task in automated driving and HD map learning. Existing methods using either onboard or aerial imagery struggle with complex lane topologies, out-of-distribution scenarios, or…
Recent years have witnessed a trend of applying context frames to boost the performance of object detection as video object detection. Existing methods usually aggregate features at one stroke to enhance the feature. These methods, however,…
Contextual information plays an important role in action recognition. Local operations have difficulty to model the relation between two elements with a long-distance interval. However, directly modeling the contextual information between…
Traffic sign detection is crucial for improving road safety and advancing autonomous driving technologies. Due to the complexity of driving environments, traffic sign detection frequently encounters a range of challenges, including low…
Vision-language models (VLMs) have recently emerged as a promising paradigm for video anomaly detection (VAD) due to their strong visual reasoning ability and natural language-based explainability. In this paper, we aim to address a key…
Contextual information provides important cues for disambiguating visually similar pixels in scene segmentation. In this paper, we introduce a neuron-level Selective Context Aggregation (SCA) module for scene segmentation, comprised of a…