Related papers: GroupFormer: Group Activity Recognition with Clust…
Multivariate time series classification (MTSC) has attracted significant research attention due to its diverse real-world applications. Recently, exploiting transformers for MTSC has achieved state-of-the-art performance. However, existing…
In this paper we present an approach for classifying the activity performed by a group of people in a video sequence. This problem of group activity recognition can be addressed by examining individual person actions and their relations.…
Spatio-temporal traffic forecasting is challenging due to complex temporal patterns, dynamic spatial structures, and diverse input formats. Although Transformer-based models offer strong global modeling, they often struggle with rigid…
In this paper, we develop a novel mobility-aware transformer-driven tiered structure (MASSFormer) based cooperative spectrum sensing method that effectively models the spatio-temporal dynamics of user movements. Unlike existing methods, our…
Most modern approaches in temporal action localization divide this problem into two parts: (i) short-term feature extraction and (ii) long-range temporal boundary localization. Due to the high GPU memory cost caused by processing long…
Recent years have witnessed a trend of applying context frames to boost the performance of object detection as video object detection. Existing methods usually aggregate features at one stroke to enhance the feature. These methods, however,…
Group Activity Recognition detects the activity collectively performed by a group of actors, which requires compositional reasoning of actors and objects. We approach the task by modeling the video as tokens that represent the multi-scale…
Recognizing human actions from untrimmed videos is an important task in activity understanding, and poses unique challenges in modeling long-range temporal relations. Recent works adopt a predict-and-refine strategy which converts an…
Temporal Action Localization (TAL) remains a fundamental challenge in video understanding, aiming to identify the start time, end time, and category of all action instances within untrimmed videos. While recent single-stage, anchor-free…
Transformer-based entropy models have gained prominence in recent years due to their superior ability to capture long-range dependencies in probability distribution estimation compared to convolution-based methods. However, previous…
Human activity intensity prediction is crucial to many location-based services. Despite tremendous progress in modeling dynamics of human activity, most existing methods overlook physical constraints of spatial interaction, leading to…
Transformer has been popular in recent crowd counting work since it breaks the limited receptive field of traditional CNNs. However, since crowd images always contain a large number of similar patches, the self-attention mechanism in…
Face clustering is a useful tool for applications like automatic face annotation and retrieval. The main challenge is that it is difficult to cluster images from the same identity with different face poses, occlusions, and image quality.…
Autonomous navigation in marine environments can be extremely challenging, especially in the presence of spatially varying flow disturbances and dynamic and static obstacles. In this work, we demonstrate that incorporating local flow field…
Vision Transformers (ViTs) have been shown to enhance visual recognition through modeling long-range dependencies with multi-head self-attention (MHSA), which is typically formulated as Query-Key-Value computation. However, the attention…
While prior work on group recommender systems (GRSs) has primarily focused on improving recommendation accuracy, most approaches assume static or predefined groups, making them unsuitable for dynamic, real-world scenarios. We reframe group…
Pedestrian attribute recognition (PAR) has received increasing attention because of its wide application in video surveillance and pedestrian analysis. Extracting robust feature representation is one of the key challenges in this task. The…
Multi-person 3D mesh recovery from videos is a critical first step towards automatic perception of group behavior in virtual reality, physical therapy and beyond. However, existing approaches rely on multi-stage paradigms, where the person…
Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized…
To capture user preference, transformer models have been widely applied to model sequential user behavior data. The core of transformer architecture lies in the self-attention mechanism, which computes the pairwise attention scores in a…