CLIP Meets Video Captioning: Concept-Aware Representation Learning Does Matter
For video captioning, "pre-training and fine-tuning" has become a de facto paradigm, where ImageNet Pre-training (INP) is usually used to encode the video content, then a task-oriented network is fine-tuned from scratch to cope with caption generation. This paper first investigates the impact of the recently proposed CLIP (Contrastive Language-Image Pre-training) on video captioning. Through the empirical study on INP vs. CLIP, we identify the potential deficiencies of INP and explore the key factors for accurate description generation. The results show that the INP-based model is tricky to capture concepts' semantics and sensitive to irrelevant background information. By contrast, the CLIP-based model significantly improves the caption quality and highlights the importance of concept-aware representation learning. With these findings, we propose Dual Concept Detection (DCD) further to inject concept knowledge into the model during training. DCD is an auxiliary task that requires a caption model to learn the correspondence between video content and concepts and the co-occurrence relations between concepts. Experiments on MSR-VTT and VATEX demonstrate the effectiveness of DCD, and the visualization results further reveal the necessity of learning concept-aware representations.
Code (1)
Tasks
Caption GenerationRepresentation LearningVideo CaptioningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding
Temporal awareness is essential for video large language models (LLMs) to understand and reason about events within long videos, enabling applications like dense video captioning and temporal video grounding in a unified…
Dense Video CaptioningTransfer LearningVideo CaptioningVideo GroundingSemantic-Aware Pretraining for Dense Video Captioning
This report describes the details of our approach for the event dense-captioning task in ActivityNet Challenge 2021. We present a semantic-aware pretraining method for dense video captioning, which empowers the learned f…
Dense CaptioningDense Video CaptioningVideo CaptioningFrom Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping
With the development of Vision-Language Pre-training Models (VLPMs) represented by CLIP and ALIGN, significant breakthroughs have been achieved for association-based visual tasks such as image classification and image-te…
DecoderImage Captioningimage-classificationImage Classification+4Progress-Aware Video Frame Captioning
While image captioning provides isolated descriptions for individual images, and video captioning offers one single narrative for an entire video clip, our work explores an important middle ground: progress-aware video c…
Image CaptioningVideo CaptioningVideo UnderstandingRETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning
Despite the significant progress of fully-supervised video captioning, zero-shot methods remain much less explored. In this paper, we propose a novel zero-shot video captioning framework named Retrieval-Enhanced Test-Tim…
Image-text matchingRetrievalTest-time AdaptationText Generation+5