相关论文: TE-TAD: Towards Full End-to-End Temporal Action De…

Multi-horizon time series forecasting has many practical applications such as demand forecasting. Accurate demand prediction is critical to help make buying and inventory decisions for supply chain management of e-commerce and physical…

Temporal Action Segmentation (TAS) is an essential task in video analysis, aiming to segment and classify continuous frames into distinct action segments. However, the ambiguous boundaries between actions pose a significant challenge for…

Event-based vision has been rapidly growing in recent years justified by the unique characteristics it presents such as its high temporal resolutions (~1us), high dynamic range (>120dB), and output latency of only a few microseconds. This…

In recent years, proposed studies on time-series anomaly detection (TAD) report high F1 scores on benchmark TAD datasets, giving the impression of clear improvements in TAD. However, most studies apply a peculiar evaluation protocol called…

With the development of artificial intelligence (AI) techniques and the increasing popularity of camera-equipped devices, many edge video analytics applications are emerging, calling for the deployment of computation-intensive AI models at…

This paper presents a novel approach for trajectory anomaly detection using an autoregressive causal-attention model, termed LM-TAD. This method leverages the similarities between language statements and trajectories, both of which consist…

Visual features are of vital importance for human action understanding in videos. This paper presents a new video representation, called trajectory-pooled deep-convolutional descriptor (TDD), which shares the merits of both hand-crafted…

The most performant spatio-temporal action localisation models use external person proposals and complex external memory banks. We propose a fully end-to-end, purely-transformer based model that directly ingests an input video, and outputs…

Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…

We consider the problem of transferring a temporal action segmentation system initially designed for exocentric (fixed) cameras to an egocentric scenario, where wearable cameras capture video data. The conventional supervised approach…

With the development of video understanding, there is a proliferation of tasks for clip-level temporal video analysis, including temporal action detection (TAD), temporal action segmentation (TAS), and generic event boundary detection…

Detecting objects in a video is a compute-intensive task. In this paper we propose CaTDet, a system to speedup object detection by leveraging the temporal correlation in video. CaTDet consists of two DNN models that form a cascaded…

Real-time video analytics on the edge is challenging as the computationally constrained resources typically cannot analyse video streams at full fidelity and frame rate, which results in loss of accuracy. This paper proposes a Transprecise…

We propose a weakly-supervised framework for action labeling in video, where only the order of occurring actions is required during training time. The key challenge is that the per-frame alignments between the input (video) and label…

We study the finite-time behaviour of the popular temporal difference (TD) learning algorithm when combined with tail-averaging. We derive finite time bounds on the parameter error of the tail-averaged TD iterate under a step-size choice…

Temporal action detection is a very important yet challenging problem, since videos in real applications are usually long, untrimmed and contain multiple action instances. This problem requires not only recognizing action categories but…

Recently, an event-based end-to-end model (SEDT) has been proposed for sound event detection (SED) and achieves competitive performance. However, compared with the frame-based model, it requires more training data with temporal annotations…

Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time adaptation (TTA) mitigates this degradation by adapting models online using unlabeled…

Typical techniques for sequence classification are designed for well-segmented sequences which have been edited to remove noisy or irrelevant parts. Therefore, such methods cannot be easily applied on noisy sequences expected in real-world…

Early Risk Detection (ERD) on the Web aims to identify promptly users facing social and health issues. Users are analyzed post-by-post, and it is necessary to guarantee correct and quick answers, which is particularly challenging in…