Related papers: T-DEED: Temporal-Discriminability Enhancer Encoder…
We propose ST-DETR, a Spatio-Temporal Transformer-based architecture for object detection from a sequence of temporal frames. We treat the temporal frames as sequences in both space and time and employ the full attention mechanisms to take…
Joint Detection and Embedding (JDE) trackers have demonstrated excellent performance in Multi-Object Tracking (MOT) tasks by incorporating the extraction of appearance features as auxiliary tasks through embedding Re-Identification task…
Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers,…
Precise Event Spotting (PES) aims to identify events and their class from long, untrimmed videos, particularly in sports. The main objective of PES is to detect the event at the exact moment it occurs. Existing methods mainly rely on…
In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component. The encoder models the global spatio-temporal feature dependencies between target objects and search regions, while the decoder…
Precise Event Spotting aims to localize fast-paced actions or events in videos with high temporal precision, a key task for applications in sports analytics, robotics, and autonomous systems. Existing methods typically process all frames…
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…
This paper presents TCE: Temporally Coherent Embeddings for self-supervised video representation learning. The proposed method exploits inherent structure of unlabeled video data to explicitly enforce temporal coherency in the embedding…
In recent years, large transformer-based video encoder models have greatly advanced state-of-the-art performance on video classification tasks. However, these large models typically process videos by averaging embedding outputs from…
Fast and accurate video object recognition, which relies on frame-by-frame video analytics, remains a challenge for resource-constrained devices such as traffic cameras. Recent advances in mobile edge computing have made it possible to…
Event cameras respond to brightness changes in the scene asynchronously and independently for every pixel. Due to the properties, these cameras have distinct features: high dynamic range (HDR), high temporal resolution, and low power…
Event-driven sensors, which produce data only when there is a change in the input signal, are increasingly used in applications that require low-latency and low-power real-time sensing, such as robotics and edge devices. To fully achieve…
Applying single image Monocular Depth Estimation (MDE) models to video sequences introduces significant temporal instability and flickering artifacts. We propose a novel approach that adapts any state-of-the-art image-based (depth)…
Text-Video retrieval is a task of great practical value and has received increasing attention, among which learning spatial-temporal video representation is one of the research hotspots. The video encoders in the state-of-the-art video…
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…
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…
Temporal action detection (TAD) is an important yet challenging task in video understanding. It aims to simultaneously predict the semantic label and the temporal interval of every action instance in an untrimmed video. Rather than…
We propose a new "Unbiased through Textual Description (UTD)" video benchmark based on unbiased subsets of existing video classification and retrieval datasets to enable a more robust assessment of video understanding capabilities. Namely,…
Visual anomaly detection is a highly challenging task, often categorized as a one-class classification and segmentation problem. Recent studies have demonstrated that the student-teacher (S-T) framework effectively addresses this challenge.…
In this paper, we investigate that the normalized coordinate expression is a key factor as reliance on hand-crafted components in query-based detectors for temporal action detection (TAD). Despite significant advancements towards an…