Zero-shot video captioning requires that a model generate high-quality captions without human-annotated video-text pairs for training. State-of-the-art approaches to the problem leverage CLIP to extract video-informed text prompts to guide language models in generating captions. However, by using representations at a single granularity (e.g., noun phrases or full sentences), these methods tend to focus on one key aspect of the scene and build a caption that ignores the rest of the visual input. To address this issue, and generate more accurate and complete captions, we propose a novel progressive multi-granularity textual prompting strategy for zero-shot video captioning. Our approach constructs three distinct memory banks, encompassing noun phrases, scene graphs of noun phrases, and entire sentences. Moreover, we introduce a category-aware retrieval mechanism that models the distribution of natural language surrounding the specific topics, to promote prompt diversity while ensuring visual relevance. Extensive experiments on both in-domain and cross-domain settings demonstrate that the proposed method consistently outperforms state-of-the-art approaches.

The limits of applicability of vision-and language models are defined by the coverage of their training data. Tasks like vision question answering (VQA) often require commonsense and factual information beyond what can be learned from task-specific datasets. This paper investigates the injection of knowledge from general-purpose knowledge bases (KBs) into vision-and-language transformers. We use an auxiliary training objective that encourages the learned representations to align with graph embeddings of matching entities in a KB. We empirically study the relevance of various KBs to multiple tasks and benchmarks. The technique brings clear benefits to knowledge-demanding question answering tasks (OK-VQA, FVQA) by capturing semantic and relational knowledge absent from existing models. More surprisingly, the technique also benefits visual reasoning tasks (NLVR2, SNLI-VE). We perform probing experiments and show that the injection of additional knowledge regularizes the space of embeddings, which improves the representation of lexical and semantic similarities. The technique is model-agnostic and can expand the applicability of any vision-and-language transformer with minimal computational overhead.