Related papers: TEA: Temporal Excitation and Aggregation for Actio…
Current architectures for video understanding mainly build upon 3D convolutional blocks or 2D convolutions with additional operations for temporal modeling. However, these methods all regard the temporal axis as a separate dimension of the…
Remarkable effectiveness of the channel or spatial attention mechanisms for producing more discernible feature representation are illustrated in various computer vision tasks. However, modeling the cross-channel relationships with channel…
Typical human actions last several seconds and exhibit characteristic spatio-temporal structure. Recent methods attempt to capture this structure and learn action representations with convolutional neural networks. Such representations,…
As a fundamental task in long-form video understanding, temporal action detection (TAD) aims to capture inherent temporal relations in untrimmed videos and identify candidate actions with precise boundaries. Over the years, various…
CLIP4Clip model transferred from the CLIP has been the de-factor standard to solve the video clip retrieval task from frame-level input, triggering the surge of CLIP4Clip-based models in the video-text retrieval domain. In this work, we…
Gait recognition is a biometric technique that identifies individuals by their unique walking styles, which is suitable for unconstrained environments and has a wide range of applications. While current methods focus on exploiting body…
Crop mapping based on satellite images time-series (SITS) holds substantial economic value in agricultural production settings, in which parcel segmentation is an essential step. Existing approaches have achieved notable advancements in…
There is significant progress in recognizing traditional human activities from videos focusing on highly distinctive actions involving discriminative body movements, body-object and/or human-human interactions. Driver's activities are…
Micro-expressions (MEs) are brief, involuntary facial movements that reveal genuine emotions, typically lasting less than half a second. Recognizing these subtle expressions is critical for applications in psychology, security, and…
This paper focuses on the temporal aspect for recognizing human activities in videos; an important visual cue that has long been undervalued. We revisit the conventional definition of activity and restrict it to Complex Action: a set of…
Spatial-temporal, channel-wise, and motion patterns are three complementary and crucial types of information for video action recognition. Conventional 2D CNNs are computationally cheap but cannot catch temporal relationships; 3D CNNs can…
Temporal human action detection aims to identify and localize action segments within untrimmed videos, serving as a pivotal task in video understanding. Despite the progress achieved by prior architectures like CNN and Transformer models,…
Class-Incremental Learning (CIL) is important in building real-world learning systems. In CLIP-based CIL, the model performs classification by comparing similarity between visual and textual embeddings obtained from template prompts, e.g.,…
We present a novel unified framework that concurrently tackles recognition and future prediction for human hand pose and action modeling. Previous works generally provide isolated solutions for either recognition or prediction, which not…
Temporal Action Detection (TAD) is an essential and challenging topic in video understanding, aiming to localize the temporal segments containing human action instances and predict the action categories. The previous works greatly rely upon…
Action classification has made great progress, but segmenting and recognizing actions from long untrimmed videos remains a challenging problem. Most state-of-the-art methods focus on designing temporal convolution-based models, but the…
Video action recognition has made significant strides, but challenges remain in effectively using both spatial and temporal information. While existing methods often focus on either spatial features (e.g., object appearance) or temporal…
Advancements in attention mechanisms have led to significant performance improvements in a variety of areas in machine learning due to its ability to enable the dynamic modeling of temporal sequences. A particular area in computer vision…
Most action recognition methods base on a) a late aggregation of frame level CNN features using average pooling, max pooling, or RNN, among others, or b) spatio-temporal aggregation via 3D convolutions. The first assume independence among…
Video anomaly detection under weak supervision presents significant challenges, particularly due to the lack of frame-level annotations during training. While prior research has utilized graph convolution networks and self-attention…