Accurate and Fast Compressed Video Captioning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916080166895616 |
|---|---|
| author | Shen, Yaojie Gu, Xin Xu, Kai Fan, Heng Wen, Longyin Zhang, Libo |
| author_facet | Shen, Yaojie Gu, Xin Xu, Kai Fan, Heng Wen, Longyin Zhang, Libo |
| contents | Existing video captioning approaches typically require to first sample video frames from a decoded video and then conduct a subsequent process (e.g., feature extraction and/or captioning model learning). In this pipeline, manual frame sampling may ignore key information in videos and thus degrade performance. Additionally, redundant information in the sampled frames may result in low efficiency in the inference of video captioning. Addressing this, we study video captioning from a different perspective in compressed domain, which brings multi-fold advantages over the existing pipeline: 1) Compared to raw images from the decoded video, the compressed video, consisting of I-frames, motion vectors and residuals, is highly distinguishable, which allows us to leverage the entire video for learning without manual sampling through a specialized model design; 2) The captioning model is more efficient in inference as smaller and less redundant information is processed. We propose a simple yet effective end-to-end transformer in the compressed domain for video captioning that enables learning from the compressed video for captioning. We show that even with a simple design, our method can achieve state-of-the-art performance on different benchmarks while running almost 2x faster than existing approaches. Code is available at https://github.com/acherstyx/CoCap. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_12867 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Accurate and Fast Compressed Video Captioning Shen, Yaojie Gu, Xin Xu, Kai Fan, Heng Wen, Longyin Zhang, Libo Computer Vision and Pattern Recognition Artificial Intelligence Existing video captioning approaches typically require to first sample video frames from a decoded video and then conduct a subsequent process (e.g., feature extraction and/or captioning model learning). In this pipeline, manual frame sampling may ignore key information in videos and thus degrade performance. Additionally, redundant information in the sampled frames may result in low efficiency in the inference of video captioning. Addressing this, we study video captioning from a different perspective in compressed domain, which brings multi-fold advantages over the existing pipeline: 1) Compared to raw images from the decoded video, the compressed video, consisting of I-frames, motion vectors and residuals, is highly distinguishable, which allows us to leverage the entire video for learning without manual sampling through a specialized model design; 2) The captioning model is more efficient in inference as smaller and less redundant information is processed. We propose a simple yet effective end-to-end transformer in the compressed domain for video captioning that enables learning from the compressed video for captioning. We show that even with a simple design, our method can achieve state-of-the-art performance on different benchmarks while running almost 2x faster than existing approaches. Code is available at https://github.com/acherstyx/CoCap. |
| title | Accurate and Fast Compressed Video Captioning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2309.12867 |