Related papers: AdaSpot: Spend Resolution Where It Matters for Pre…

Precise Event Spotting (PES) in sports videos requires frame-level recognition of fine-grained actions from single-camera footage. Existing PES models typically incorporate lightweight temporal modules such as the Gate Shift Module (GSM) or…

Adversarial robustness assessment for video recognition models has raised concerns owing to their wide applications on safety-critical tasks. Compared with images, videos have much high dimension, which brings huge computational costs when…

In this paper, we introduce AdaSelection, an adaptive sub-sampling method to identify the most informative sub-samples within each minibatch to speed up the training of large-scale deep learning models without sacrificing model performance.…

The goal in episodic memory (EM) is to search a long egocentric video to answer a natural language query (e.g., "where did I leave my purse?"). Existing EM methods exhaustively extract expensive fixed-length clip features to look everywhere…

In recent years, video analysis tools for automatically extracting meaningful information from videos are widely studied and deployed. Because most of them use deep neural networks which are computationally expensive, feeding only a subset…

Precise action spotting has attracted considerable attention due to its promising applications. While existing methods achieve substantial performance by employing well-designed model architecture, they overlook a significant challenge: the…

Analyzing Fast, Frequent, and Fine-grained (F$^3$) events presents a significant challenge in video analytics and multi-modal LLMs. Current methods struggle to identify events that satisfy all the F$^3$ criteria with high accuracy due to…

Existing supervised action segmentation methods depend on the quality of frame-wise classification using attention mechanisms or temporal convolutions to capture temporal dependencies. Even boundary detection-based methods primarily depend…

Fast and accurate auto-focus in adverse conditions remains an arduous task. The emergence of event cameras has opened up new possibilities for addressing the challenge. This paper presents a new high-speed and accurate event-based focusing…

Generating high-fidelity long videos with Diffusion Transformers (DiTs) is often hindered by significant latency, primarily due to the computational demands of attention mechanisms. For instance, generating an 8-second 720p video (110K…

Most existing action quality assessment methods rely on the deep features of an entire video to predict the score, which is less reliable due to the non-transparent inference process and poor interpretability. We argue that understanding…

The rapid growth of video-text data presents challenges in storage and computation during training. Online learning, which processes streaming data in real-time, offers a promising solution to these issues while also allowing swift…

In recent years, there has been a growing demand for improved autonomy for in-orbit operations such as rendezvous, docking, and proximity maneuvers, leading to increased interest in employing Deep Learning-based Spacecraft Pose Estimation…

In industrial applications requiring real-time feedback, such as quality control and robotic manipulation, the demand for high-speed and accurate pose estimation remains critical. Despite advances improving speed and accuracy in pose…

Object detection in videos is an important task in computer vision for various applications such as object tracking, video summarization and video search. Although great progress has been made in improving the accuracy of object detection…

The recently proposed action spotting task consists in finding the exact timestamp in which an event occurs. This task fits particularly well for soccer videos, where events correspond to salient actions strictly defined by soccer rules (a…

Despite great progress, text-driven long video editing is still notoriously challenging mainly due to excessive memory overhead. Although recent efforts have simplified this task into a two-step process of keyframe translation and…

Deploying tiny object perception on edge platforms is challenging because practical systems must satisfy both strict compute budgets and end-to-end latency constraints. A common strategy is to first select a small number of candidate…

Event cameras can capture pixel-level illumination changes with very high temporal resolution and dynamic range. They have received increasing research interest due to their robustness to lighting conditions and motion blur. Two main…

Accurate prediction of application performance is critical for enabling effective scheduling and resource management in resource-constrained dynamic edge environments. However, achieving predictable performance in such environments remains…