Related papers: AdaSpot: Spend Resolution Where It Matters for Pre…
Action spotting is crucial in sports analytics as it enables the precise identification and categorization of pivotal moments in sports matches, providing insights that are essential for performance analysis and tactical decision-making.…
Real-time video analytics systems typically place models with fewer weights on edge devices to reduce latency. The distribution of video content features may change over time for various reasons (i.e. light and weather change) , leading to…
In this paper, we address the challenging problem of action recognition, using event-based cameras. To recognise most gestural actions, often higher temporal precision is required for sampling visual information. Actions are defined by…
Multi-view learning primarily aims to fuse multiple features to describe data comprehensively. Most prior studies implicitly assume that different views share similar dimensions. In practice, however, severe dimensional disparities often…
Association football is a complex and dynamic sport, with numerous actions occurring simultaneously in each game. Analyzing football videos is challenging and requires identifying subtle and diverse spatio-temporal patterns. Despite recent…
Innovative enhancement in embedded system platforms, specifically hardware accelerations, significantly influence the application of deep learning in real-world scenarios. These innovations translate human labor efforts into automated…
Streaming video models should respond the moment an event unfolds, not after the moment has passed. Yet existing online VideoQA benchmarks remain largely retrospective. They pause the video at fixed timestamps, pose questions about current…
The task of action spotting consists in both identifying actions and precisely localizing them in time with a single timestamp in long, untrimmed video streams. Automatically extracting those actions is crucial for many sports applications,…
Despite the rapid advancement in the field of image recognition, the processing of high-resolution imagery remains a computational challenge. However, this processing is pivotal for extracting detailed object insights in areas ranging from…
Video super-resolution (VSR) has many applications that pose strict causal, real-time, and latency constraints, including video streaming and TV. We address the VSR problem under these settings, which poses additional important challenges…
In this paper, we introduce T-DEED, a Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in sports videos. T-DEED addresses multiple challenges in the task, including the need for discriminability among frame…
Video text spotting is still an important research topic due to its various real-applications. Previous approaches usually fall into the four-staged pipeline: text detection in individual images, framewisely recognizing localized text…
With the great success of text-conditioned diffusion models in creative text-to-image generation, various text-driven image editing approaches have attracted the attentions of many researchers. However, previous works mainly focus on…
Video depth estimation is essential for providing 3D scene structure in applications ranging from autonomous driving to mixed reality. Current end-to-end video depth models have established state-of-the-art performance. Although current…
State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time, and robustness. With the successful concept of pixel-wise matching and sparse-to-dense interpolation, we push the limits of scene flow estimation.…
The task of action detection aims at deducing both the action category and localization of the start and end moment for each action instance in a long, untrimmed video. While vision Transformers have driven the recent advances in video…
Few-shot segmentation (FSS) aims to rapidly learn novel class concepts from limited examples to segment specific targets in unseen images, and has been widely applied in areas such as medical diagnosis and industrial inspection. However,…
Long-form clinical videos are central to visual evidence-based decision-making, with growing importance for applications such as surgical robotics and related settings. However, current multimodal large language models typically process…
We propose a novel recurrent attentional structure to localize and recognize objects jointly. The network can learn to extract a sequence of local observations with detailed appearance and rough context, instead of sliding windows or…
The computational cost of softmax-based attention in transformers limits their applicability to long-context tasks. Adaptive sparsity, of which $\alpha$-entmax attention is an example, offers a flexible data-dependent alternative, but…