paper-with-me

Papers

CLIP Meets Video Captioning: Concept-Aware Representation Learning Does Matter

2021-11-30 · Bang Yang, Tong Zhang, Yuexian Zou

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.

📄 PDF Abstract BibTeX arXiv:2111.15162

Code (1)

yangbang18/CLIP-Captioner 공식 구현 pytorch

Tasks

Caption GenerationRepresentation LearningVideo Captioning

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding

2024-11-25 · CVPR 2025 1 · Andong Deng, Zhongpai Gao, Anwesa Choudhuri, Benjamin Planche 외

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 Grounding

Semantic-Aware Pretraining for Dense Video Captioning

2022-04-13 · Teng Wang, Zhu Liu, Feng Zheng, Zhichao Lu 외

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 Captioning

From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping

2023-04-26 · Junyang Wang, Ming Yan, Yi Zhang, Jitao Sang

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+4

Progress-Aware Video Frame Captioning

2024-12-03 · CVPR 2025 1 · Zihui Xue, Joungbin An, Xitong Yang, Kristen Grauman

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 Understanding

RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning

2024-05-11 · Yunchuan Ma, Laiyun Qing, Guorong Li, Yuankai Qi 외

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