相关论文: Do we really need temporal convolutions in action …

In interactive object segmentation a user collaborates with a computer vision model to segment an object. Recent works employ convolutional neural networks for this task: Given an image and a set of corrections made by the user as input,…

Recent transformer-based offline video instance segmentation (VIS) approaches achieve encouraging results and significantly outperform online approaches. However, their reliance on the whole video and the immense computational complexity…

Rapid progress and superior performance have been achieved for skeleton-based action recognition recently. In this article, we investigate this problem under a cross-dataset setting, which is a new, pragmatic, and challenging task in…

Temporal action segmentation (TAS) demands dense temporal supervision, yet most of the annotation cost in untrimmed videos is spent identifying and refining action transitions, where segmentation errors concentrate and small temporal shifts…

Action quality assessment (AQA) is an active research problem in video-based applications that is a challenging task due to the score variance per frame. Existing methods address this problem via convolutional-based approaches but suffer…

With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions…

Temporal action segmentation (TAS) divides untrimmed videos into labeled action segments. While fully supervised methods have advanced the field, challenges such as action variability, ambiguous boundaries, and high annotation costs remain,…

Transformers have emerged as a competitive alternative to convnets in vision tasks, yet they lack the architectural inductive bias of convnets, which may hinder their potential performance. Specifically, Vision Transformers (ViTs) are not…

The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers…

Time series forecasting is widely used in the fields of equipment life cycle forecasting, weather forecasting, traffic flow forecasting, and other fields. Recently, some scholars have tried to apply Transformer to time series forecasting…

This study proposes an unsupervised anomaly detection method for distributed backend service systems, addressing practical challenges such as complex structural dependencies, diverse behavioral evolution, and the absence of labeled data.…

In this work, we combine 3D convolution with late temporal modeling for action recognition. For this aim, we replace the conventional Temporal Global Average Pooling (TGAP) layer at the end of 3D convolutional architecture with the…

Human action recognition has become an important research focus in computer vision due to the wide range of applications where it is used. 3D Resnet-based CNN models, particularly MC3, R3D, and R(2+1)D, have different convolutional filters…

We propose a novel approach to the action segmentation task for long, untrimmed videos, based on solving an optimal transport problem. By encoding a temporal consistency prior into a Gromov-Wasserstein problem, we are able to decode a…

This paper presents a deep learning framework for medical video segmentation. Convolution neural network (CNN) and transformer-based methods have achieved great milestones in medical image segmentation tasks due to their incredible semantic…

In video transformers, the time dimension is often treated in the same way as the two spatial dimensions. However, in a scene where objects or the camera may move, a physical point imaged at one location in frame $t$ may be entirely…

Few-shot video object segmentation (FS-VOS) aims at segmenting video frames using a few labelled examples of classes not seen during initial training. In this paper, we present a simple but effective temporal transductive inference (TTI)…

We propose Token Turing Machines (TTM), a sequential, autoregressive Transformer model with memory for real-world sequential visual understanding. Our model is inspired by the seminal Neural Turing Machine, and has an external memory…

Skeleton-based action recognition, which classifies human actions based on the coordinates of joints and their connectivity within skeleton data, is widely utilized in various scenarios. While Graph Convolutional Networks (GCNs) have been…

Video topic segmentation unveils the coarse-grained semantic structure underlying videos and is essential for other video understanding tasks. Given the recent surge in multi-modal, relying solely on a single modality is arguably…