Generation-Augmented Video Corpus Moment Retrieval

Training-Free Video Corpus Moment Retrieval via Synergistic Collaboration and Adaptive Calibration

Video Corpus Moment Retrieval (VCMR) is pivotal to multimodal understanding. However, existing methods rely heavily on large-scale annotated data, which limits their generalization and scalability. To address this issue, we propose a training-free VCMR framework, termed Synergistic Collaboration and Adaptive Calibration (SCAC), enabling effective semantic parsing and precise temporal localization without parameter updates. SCAC introduces a Query Event Chain Generation module that leverages large language models to transform complex textual queries into structured event chains, while a Video Event Chain Generation module represents videos as semantically coherent event chains through subtitle segmentation and keyframe aggregation. Built on these structured representations, SCAC performs Event-Chain-Based Cross-Modal Retrieval with mean-variance joint scoring to suppress local mismatches and reinforce global consistency. During localization, a Synergy-Calibration Mechanism dynamically refines temporal boundaries via profit-setback feedback. Extensive experiments show that SCAC achieves comparable or superior results to supervised counterparts under training-free conditions, demonstrating strong cross-modal generalization and adaptive capability. The code of our method is available at https://github.com/cyanlll/SCAC

Mitigating Modality and Language-Style Gaps for Zero-Shot Video Moment Retrieval

This work proposes Self-SiMS, a self-similarity-based Moment Proposal and Scoring that exploits intrinsic relationships within videos, enabling robust span generation and scoring and introduces a query-aware MLLM-based reasoning stage to further sharpen alignment between text and video.

A Multimodal Retrieval-Augmented Generation Framework for Context-Aware Semantic Querying

Retrieval-Augmented Generation (RAG) has established itself as a compelling strategy for grounding large language model outputs in documentary evidence. However, production deployments continue to rely almost exclusively on homogeneous text corpora, even as enterprise repositories grow increasingly heterogeneous blending technical schematics, radiological images, annotated diagrams, and unstructured prose within the same archival system. This mismatch between system design and data reality motivates the present work. We propose a Multimodal RAG framework that unifies text and image retrieval through four tightly coupled components: a dual-stream embedding engine, a learned four-class AI query router, an adaptive confidence threshold, and a session-aware context store. Text is encoded with the allmpnet-base-v2 Sentence Transformer; images are embedded in the same 768-dimensional space via a domain-adapted CLIP ViT-L/14 model fine-tuned on approximately 120,000 technical and clinical text-image pairs. Concatenating 768-d vectors yields a 1,536-d composite query that drives a single approximate nearest-neighbor (ANN) search simultaneously across both modalities. A fine-tuned DistilBERT router assigns each query to one of four retrieval pathways text-only, image-only, hybrid, or conversational at 91.3% accuracy. Experiments were run on three enterprise corpora (engineering manuals, clinical case summaries, and legal paperwork) with the results being a mean F1@5 of 0.90, an increase of 22% over a dense text-only baseline, and a reduction of 49% in the number of hallucinations. The median first-token latency is 1.34s, which meets the interactive-use target deployment-contexts. These results show that it is possible to implement modality-aware retrieval in a simple and realistic setting with real-world organizational constraints and that the results are reproducible.

Doc-REFRAG: Rethinking Multimodal Document Retrieval-Augmented Generation

Real-world knowledge resides in multimodal documents, necessitating retrieval-augmented generation (RAG) for accurate question answering. However, existing multimodal RAG models are primarily designed for single-image or closed-document settings and exhibit limited accuracy in realistic multi-image scenarios. Moreover, processing numerous retrieved images incurs substantial computational overhead from irrelevant visual tokens. To address these challenges, we introduce DocLongRAG, a large-scale dataset of 343K question--answer pairs, each associated with an average of 37.4 retrieved images to reflect authentic RAG workflows. Building on this dataset, we propose Doc-REFRAG, a question-guided framework that compresses visual tokens into coarse chunks and selectively expands question-relevant ones via a lightweight RL-based selector. Experiments on six benchmarks show that Doc-REFRAG outperforms eleven strong baselines, achieving state-of-the-art accuracy with significantly lower inference latency. Our resources are available at https://github.com/Collab-Gen/Doc-REFRAG.

Anchor-Guided Discriminative Semantic Expansion for Point-Supervised Video Moment Localization

With the rapid growth of real-world untrimmed videos, video moment localization (VML) has become a fundamental task in query-guided video understanding, aiming to identify the temporal moment that semantically matches a natural language query. Although fully supervised methods have achieved promising performance, their reliance on precise start–end annotations makes them difficult to scale to open-domain video scenarios, where visual contents are diverse, distracting contexts are common, and annotation resources are limited. Point-supervised VML provides a more data-efficient alternative by requiring only a single annotated point inside the target moment. However, such sparse supervision makes it challenging to infer the complete query-relevant interval and to suppress semantically similar distractors. To address these challenges, we propose an anchor-guided discriminative semantic expansion (ADSE) framework. ADSE treats the annotated point as a reliable semantic anchor, learns anchor-centered cross-modal alignment to generate a temporal relevance curve, and adaptively expands the anchor into a coherent target moment by integrating query relevance and temporal semantic continuity. Meanwhile, an anchor-guided discriminative learning strategy mines high-confidence anchor-excluded intervals as hard negatives, and an inside–outside separation objective further distinguishes target moments from surrounding contexts. Extensive experiments on public benchmarks demonstrate the effectiveness of ADSE and show consistent improvements over existing point-supervised methods under sparse point-level supervision.

Strengthen-then-retrieve: semantic enrichment and reconstruction feedback for text-video retrieval