# Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Moment

arXiv: https://arxiv.org/abs/2307.02682 · HTML: https://mlsanity.com/paper/2307.02682/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 53 references that are in the map.
- First posted on arXiv 5 Jul 2023.

## Builds on (most cited first, 30 of 38)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [Towards Automatic Learning of Procedures from Web Instructional Videos](https://mlsanity.com/paper/1703.09788/) (2017)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning](https://mlsanity.com/paper/2302.14115/) (2023)
- [Local-Global Video-Text Interactions for Temporal Grounding](https://mlsanity.com/paper/2004.07514/) (2020)
- [Dense Regression Network for Video Grounding](https://mlsanity.com/paper/2004.03545/) (2020)
- [SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning](https://mlsanity.com/paper/2111.13196/) (2021)
- [ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic](https://mlsanity.com/paper/2111.14447/) (2021)
- [MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment](https://mlsanity.com/paper/1812.00087/) (2018)
- [Linearly Mapping from Image to Text Space](https://mlsanity.com/paper/2209.15162/) (2022)
- [End-to-End Dense Video Captioning with Parallel Decoding](https://mlsanity.com/paper/2108.07781/) (2021)
- [Multi-modal Dense Video Captioning](https://mlsanity.com/paper/2003.07758/) (2020)
- [Reconstruction Network for Video Captioning](https://mlsanity.com/paper/1803.11438/) (2018)
- [Weakly Supervised Video Moment Retrieval From Text Queries](https://mlsanity.com/paper/1904.03282/) (2019)
- [MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning](https://mlsanity.com/paper/2112.05253/) (2021)
- [Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention](https://mlsanity.com/paper/1908.07236/) (2019)
- [A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer](https://mlsanity.com/paper/2005.08271/) (2020)
- [Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning](https://mlsanity.com/paper/1804.00100/) (2018)
- [Weakly Supervised Dense Event Captioning in Videos](https://mlsanity.com/paper/1812.03849/) (2018)
- [Video Captioning via Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1711.11135/) (2017)
- [Video Captioning with Transferred Semantic Attributes](https://mlsanity.com/paper/1611.07675/) (2016)
- [VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval](https://mlsanity.com/paper/2008.10238/) (2020)

## Built on by (most cited first, 4 of 4)

- [Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols](https://mlsanity.com/paper/2311.02538/) (2023)
- [RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning](https://mlsanity.com/paper/2405.07046/) (2024)
- [T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding](https://mlsanity.com/paper/2603.06973/) (2026)
- [How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey](https://mlsanity.com/paper/2412.08158/) (2024)

## Abstract (arXiv)

Dense video captioning, a task of localizing meaningful moments and generating relevant captions for videos, often requires a large, expensive corpus of annotated video segments paired with text. In an effort to minimize the annotation cost, we propose ZeroTA, a novel method for dense video captioning in a zero-shot manner. Our method does not require any videos or annotations for training; instead, it localizes and describes events within each input video at test time by optimizing solely on the input. This is accomplished by introducing a soft moment mask that represents a temporal segment in the video and jointly optimizing it with the prefix parameters of a language model. This joint optimization aligns a frozen language generation model (i.e., GPT-2) with a frozen vision-language contrastive model (i.e., CLIP) by maximizing the matching score between the generated text and a moment within the video. We also introduce a pairwise temporal IoU loss to let a set of soft moment masks capture multiple distinct events within the video. Our method effectively discovers diverse significant events within the video, with the resulting captions appropriately describing these events. The empirical results demonstrate that ZeroTA surpasses zero-shot baselines and even outperforms the state-of-the-art few-shot method on the widely-used benchmark ActivityNet Captions. Moreover, our method shows greater robustness compared to supervised methods when evaluated in out-of-domain scenarios. This research provides insight into the potential of aligning widely-used models, such as language generation models and vision-language models, to unlock a new capability: understanding temporal aspects of videos.