Spatio-Temporal Ranked-Attention Networks for Video Captioning
원문 초록
Generating video descriptions automatically is a challenging task that involves a complex interplay between spatio-temporal visual features and language models. Given that videos consist of spatial (frame-level) features and their temporal evolutions, an effective captioning model should be able to attend to these different cues selectively. To this end, we propose a Spatio-Temporal and Temporo-Spatial (STaTS) attention model which, conditioned on the language state, hierarchically combines spatial and temporal attention to videos in two different orders: (i) a spatio-temporal (ST) sub-model, which first attends to regions that have temporal evolution, then temporally pools the features from these regions; and (ii) a temporo-spatial (TS) sub-model, which first decides a single frame to attend to, then applies spatial attention within that frame. We propose a novel LSTM-based temporal ranking function, which we call ranked attention, for the ST model to capture action dynamics. Our entire framework is trained end-to-end. We provide experiments on two benchmark datasets: MSVD and MSR-VTT. Our results demonstrate the synergy between the ST and TS modules, outperforming recent state-of-the-art methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks
video-SALMONN 2: Captioning-Enhanced Audio-Visual Large Language Models
FLASH: Latent-Aware Semi-Autoregressive Speculative Decoding for Multimodal Tasks
FocusedAD: Character-centric Movie Audio Description
Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting
Pretrained Image-Text Models are Secretly Video Captioners
토론
이 논문과 연결된 포럼 글이 아직 없습니다.