CORTEXA
← Browse
arxivcs.CV2026-07-21

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

Jihyun Lee, Cheol-Ho Cho, Woojin Jun, Woojin Jeong, Jae-Pil Heo

Zero-shot video moment retrieval aims to overcome the limitations of traditional approaches that require large-scale datasets annotated with text and its relevant temporal spans. Despite advances in pre-trained vision-language models and multimodal large language models, existing ZMR methods still heavily depend on query-to-video content similarity, making them vulnerable to modality and language-style gaps. These gaps lead to unreliable span proposals and unstable moment retrieval results. To address this issue, we propose Self-Similarity-based Moment Proposal and Scoring that instead exploits intrinsic relationships within videos, enabling robust span generation and scoring. By deriving self-similarity only from the video content, we circumvent the noisy and mismatched patterns of query-frame or query-caption similarities, thereby mitigating both modality and language-style gaps. Furthermore, we introduce a query-aware MLLM-based reasoning stage to further sharpen alignment between text and video. Extensive experiments demonstrate that Self-SiMS achieves state-of-the-art performance across ZMR benchmarks.

View free PDFSource page

Related papers

arxivcs.CVcs.IR2026-07-14

Towards Vision-Free CIR: Attribute-Augmented Scoring and LLM-Based Reranking for Zero-Shot Composed Image Retrieval

Ryotaro Shimada, Yu-Chieh Lin, Yuji Nozawa, Youyang Ng, Osamu Torii, Yusuke Matsui

Recent work has shown that "Vision-Free'' approaches (representing images as text) can be effective for standard image retrieval tasks. However, it remains unclear whether this paradigm can effectively handle a more complex, multimodal task, Composed Image Retrieval (CIR), due to…

View free PDFSource page
arxivcs.CV2026-07-10

Promptable Concept Segmentation from Above: Evaluating SAM 3's Zero-Shot and One-Shot Capabilities in Remote Sensing

Mohammad Dabaja, Turgay Celik

The deployment of large-scale foundation models, such as the Segment Anything Model 3 (SAM 3), promises a transition toward open-vocabulary, training-free computer vision. However, their capacity to generalize out-of-distribution to the complex, top-down geometric structures of E…

View free PDFSource page
arxivcs.CVcs.AI2026-07-15

GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid Reasoning

Kaicong Huang, Weiheng Oh, Jack M. Reilly, Thomas Guggisberg, Ruimin Ke

Transit video understanding can provide valuable fine-grained data that conventional passenger counters and fare systems cannot capture. However, supervised video models require task-specific annotations, while applying vision-language models (VLMs) directly to long onboard video…

View free PDFSource page
arxivcs.CVcs.AI2026-07-18

TellTale: Blending Multi-Instance LoRA Text Encoders and a Zero-Shot LLM Judge for Ambivalence/Hesitancy Recognition in Videos

Abdel-Karim Al-Tamimi, Ali Rodan

We present TellTale, a text-only approach to ambivalence/hesitancy (A/H) recognition in interview videos, evaluated on the BAH dataset as part of the 3rd A/H Video Recognition Challenge (11th ABAW Workshop, ECCV 2026). Although the dataset provides video, audio, facial crops, and…

View free PDFSource page
arxivcs.CV2026-07-17

When Can Test-Time Adaptation Help Zero-Shot CT Vision-Language Models?

Ailar Mahdizadeh, Puria Azadi Moghadam, Xiangteng He, Leonid Sigal

3D CT vision-language models (VLMs) classify abnormalities from text prompts in a zero-shot manner, enabling cross-institution deployment where labels are scarce and clinical tasks shift faster than supervised models can be retrained. A real CT scan, however, typically contains s…

View free PDFSource page
arxivcs.CV2026-07-10

TextileNet: Towards Zero-shot Text-style Segmentation of Manuscripts

Anguelos Nicolaou, Antonella Ambrosio, Desiree Di Donato, Georg Vogeler

Automatic writer identification systems have progressed remarkably in recent years, yet their deployment in archival paleography remains limited by the scarcity of labeled training data, open scribe sets, and degraded image quality. We present TextileNet, a fully convolutional mu…

View free PDFSource page