5 papers
NBA_Streaming: A Large-Scale Benchmark for Fine-Grained Basketball Commentary Generation in Continuous Streams
Lifang Wu, Yuyang Wu, Yangdong Gao +3
Live basketball commentary generation requires determining when an event is sufficiently observable and describing it before subsequent events unfold. However, existing methods are…
Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning
Zeyu Xi, Haoying Sun, Yaofei Wu +5
Existing sports video captioning methods often focus on the action yet overlook player identities, limiting their applicability. Although some methods integrate extra information t…
VicKAM: Visual Conceptual Knowledge Guided Action Map for Weakly Supervised Group Activity Recognition
Zhuming Wang, Yihao Zheng, Jiarui Li +5
Existing weakly supervised group activity recognition methods rely on object detectors or attention mechanisms to capture key areas automatically. However, they overlook the semant…
Knowledge Guided Entity-aware Video Captioning and A Basketball Benchmark
Zeyu Xi, Ge Shi, Xuefen Li +5
Despite the recent emergence of video captioning models, how to generate the text description with specific entity names and fine-grained actions is far from being solved, which ho…
Knowledge Augmented Relation Inference for Group Activity Recognition
Xianglong Lang, Zhuming Wang, Zun Li +4
Most existing group activity recognition methods construct spatial-temporal relations merely based on visual representation. Some methods introduce extra knowledge, such as action…