Table III from Learning Label Semantics for Weakly Supervised Group Activity Recognition | Semantic Scholar (2024)

This work proposes a novel model for group activity recognition that depends neither on bounding box labels nor on object detector, and localizes and encodes partial contexts of a group activity by leveraging the attention mechanism, and represents a video clip as a set of partial context embeddings.

This paper proposes a new reasoning paradigm to incorporate global contextual information, Transformer based Context Encoding (TCE) module, which enhances individual representation by encodingglobal contextual information to individual features and refining the aggregated information.

A fast weakly supervised deep learning architecture for collective activity recognition and a latent embedding scheme for mining person-group interactive relationship to get rid of the use of any pairwise relation between people and the individual action labels as well are proposed.

This framework is designed to locate active spatial positions and use them as visual tokens to infer the relations for token embeddings and demonstrates that the proposed framework is competitive against existing schemes that require more laboring and computation to generate labels.

This paper proposes to build a flexible and efficient Actor Relation Graph (ARG) to simultaneously capture the appearance and position relation between actors, and performs extensive experiments on two standard group activity recognition datasets.

A unified deep learning framework to Disentangle, Embed and Rank the corresponding label cues and proposes an embedding operation from a metric learning perspective to pull the relevant label vectors together and push irrelevant label vectors away.

A novel method based on deep reinforcement learning to progressively refine the low-level features and high-level relations of group activities and construct a semantic relation graph (SRG) to explicitly model the relations among persons.

A method to integrate graphical models and deep neural networks into a joint framework that uses a sequential inference modeled by a recurrent neural network and demonstrates the potential of this model to handle highly structured learning tasks.

This work proposes a multi-label classification model based on Graph Convolutional Network (GCN), and proposes a novel re-weighted scheme to create an effective label correlation matrix to guide information propagation among the nodes in GCN.

...

...