A review of multimodal human activity recognition with special emphasis on classification, applications, challenges and future directions
Human activity recognition (HAR) is one of the most important and challenging problems in
the computer vision. It has critical application in wide variety of tasks including gaming …
the computer vision. It has critical application in wide variety of tasks including gaming …
Convolutional neural networks or vision transformers: Who will win the race for action recognitions in visual data?
Understanding actions in videos remains a significant challenge in computer vision, which
has been the subject of several pieces of research in the last decades. Convolutional neural …
has been the subject of several pieces of research in the last decades. Convolutional neural …
Videomae v2: Scaling video masked autoencoders with dual masking
Scale is the primary factor for building a powerful foundation model that could well
generalize to a variety of downstream tasks. However, it is still challenging to train video …
generalize to a variety of downstream tasks. However, it is still challenging to train video …
Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training
Pre-training video transformers on extra large-scale datasets is generally required to
achieve premier performance on relatively small datasets. In this paper, we show that video …
achieve premier performance on relatively small datasets. In this paper, we show that video …
Uniformer: Unifying convolution and self-attention for visual recognition
It is a challenging task to learn discriminative representation from images and videos, due to
large local redundancy and complex global dependency in these visual data. Convolution …
large local redundancy and complex global dependency in these visual data. Convolution …
Actionclip: A new paradigm for video action recognition
The canonical approach to video action recognition dictates a neural model to do a classic
and standard 1-of-N majority vote task. They are trained to predict a fixed set of predefined …
and standard 1-of-N majority vote task. They are trained to predict a fixed set of predefined …
Tdn: Temporal difference networks for efficient action recognition
Temporal modeling still remains challenging for action recognition in videos. To mitigate this
issue, this paper presents a new video architecture, termed as Temporal Difference Network …
issue, this paper presents a new video architecture, termed as Temporal Difference Network …
Uniformer: Unified transformer for efficient spatiotemporal representation learning
It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-
dimensional videos, due to large local redundancy and complex global dependency …
dimensional videos, due to large local redundancy and complex global dependency …
Bidirectional cross-modal knowledge exploration for video recognition with pre-trained vision-language models
Vision-language models (VLMs) pre-trained on large-scale image-text pairs have
demonstrated impressive transferability on various visual tasks. Transferring knowledge …
demonstrated impressive transferability on various visual tasks. Transferring knowledge …
Vidtr: Video transformer without convolutions
Abstract We introduce Video Transformer (VidTr) with separable-attention for video
classification. Comparing with commonly used 3D networks, VidTr is able to aggregate …
classification. Comparing with commonly used 3D networks, VidTr is able to aggregate …