Related papers: TAPTRv3: Spatial and Temporal Context Foster Robus…
Visual tracking has made significant improvements in the past few decades. Most existing state-of-the-art trackers 1) merely aim for performance in ideal conditions while overlooking the real-world conditions; 2) adopt the…
Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…
In static monitoring cameras, useful contextual information can stretch far beyond the few seconds typical video understanding models might see: subjects may exhibit similar behavior over multiple days, and background objects remain static.…
We introduce TAPIP3D, a novel approach for long-term 3D point tracking in monocular RGB and RGB-D videos. TAPIP3D represents videos as camera-stabilized spatio-temporal feature clouds, leveraging depth and camera motion information to lift…
In this paper, we propose a simple and strong framework for Tracking Any Point with TRansformers (TAPTR). Based on the observation that point tracking bears a great resemblance to object detection and tracking, we borrow designs from…
In this paper, we present TAPTRv2, a Transformer-based approach built upon TAPTR for solving the Tracking Any Point (TAP) task. TAPTR borrows designs from DEtection TRansformer (DETR) and formulates each tracking point as a point query,…
Self-attention learns pairwise interactions to model long-range dependencies, yielding great improvements for video action recognition. In this paper, we seek a deeper understanding of self-attention for temporal modeling in videos. We…
Video Large Language Models (Video LLMs) have shown promising capabilities in video comprehension, yet they struggle with tracking temporal changes and reasoning about temporal relationships. While previous research attributed this…
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…
Most deep trackers still follow the guidance of the siamese paradigms and use a template that contains only the target without any contextual information, which makes it difficult for the tracker to cope with large appearance changes, rapid…
We propose a novel algorithm for accelerating dense long-term 3D point tracking in videos. Through analysis of existing state-of-the-art methods, we identify two major computational bottlenecks. First, transformer-based iterative tracking…
Referring Video Segmentation (RVOS) aims to segment objects in videos given linguistic expressions. The key to solving RVOS is to extract long-range temporal context information from the interactions of expressions and videos to depict the…
Humans perceive and understand real-world spaces through a stream of visual observations. Therefore, the ability to streamingly maintain and update spatial evidence from potentially unbounded video streams is essential for spatial…
Temporal contexts among consecutive frames are far from being fully utilized in existing visual trackers. In this work, we present TCTrack, a comprehensive framework to fully exploit temporal contexts for aerial tracking. The temporal…
Most existing video moment retrieval methods rely on temporal sequences of frame- or clip-level features that primarily encode global visual and semantic information. However, such representations often fail to capture fine-grained object…
Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between…
This paper is on long-term video understanding where the goal is to recognise human actions over long temporal windows (up to minutes long). In prior work, long temporal context is captured by constructing a long-term memory bank consisting…
Generating video descriptions automatically is a challenging task that involves a complex interplay between spatio-temporal visual features and language models. Given that videos consist of spatial (frame-level) features and their temporal…
This paper proposes a method for long-term action anticipation (LTA), the task of predicting action labels and their duration in a video given the observation of an initial untrimmed video interval. We build on an encoder-decoder…
Video classification is highly important with wide applications, such as video search and intelligent surveillance. Video naturally consists of static and motion information, which can be represented by frame and optical flow. Recently,…