CORTEXA
← Browse
arxivcs.CV2026-06-29

Rigel: Self-Distilled Score Adaptation for Image and Video Captioning Evaluation

Shuitsu Koyama, Kazuki Matsuda, Yuiga Wada, Shinnosuke Hirano, Daichi Yashima, Komei Sugiura

Automatic evaluation of image and video captioning is essential for benchmarking multimodal systems, although standard evaluation metrics show limited alignment with human judgments. Recent approaches using large language models (LLMs), commonly referred to as LLM-as-a-Judge, have improved alignment with human judgments but still suffer from a mismatch between large-vocabulary language modeling and evaluation over a small label set. To address this, we propose Rigel, an automatic evaluation metric for image and video captioning, based on self-distilled score adaptation. The metric employs an evaluation-specific scoring head distilled from a frozen LLM, which captures judgment signals in a task-aligned space without relying on large-vocabulary token sets. We then refine the LLM backbone with human judgment data. To train Rigel, we constructed the Vid-Lepus dataset, which contains 3,338 video clips, 33,380 reference captions, and 5,637 candidate captions. Experiments on multiple benchmarks show that Rigel outperforms state-of-the-art metrics, achieving over 10-point improvements on ActivityNet-Fact in the reference-free setting.

View free PDFSource page

Related papers

arxivcs.CVcs.AIcs.HC2026-07-09

VEGAS: Human-Aligned Video Caption Evaluation via Gaze

Shenghui Chen, Po-han Li, Ximeng Sun, Shijia Yang, Emad Barsoum, Zicheng Liu, et al.

Vision-language models excel at video captioning, yet typically generate descriptions that fail to capture individual viewers' attention. We propose VEGAS (Video caption Evaluation via GAze Score), a training-free metric that leverages test-time gaze to sample personalized, atten…

View free PDFSource page
arxivcs.CVcs.AI2026-07-23

Visual Contrastive Self-Distillation

Yijun Liang, Yunjie Tian, Yijiang Li, Yuqi Jia, Furong Huang, Tianyi Zhou, et al.

On-policy self-distillation (OPSD) is promising as it removes the external teacher required by on-policy distillation (OPD), yet it still needs asymmetric information between teacher and student to ensure that the self-teacher provides a stronger learning signal than the student.…

View free PDFSource page
arxivcs.CV2026-07-09

OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators

Hongyu Liu, Chun Wang, Feng Gao, Xuanhua He, Yue Ma, Ziyu Wan, et al.

We propose OPSD-V, an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models. Existing few-step AR video generators can produce long videos with low latency, but still suffer from error accumulation and weakened motion dynamics…

View free PDFSource page
arxivcs.CV2026-07-05

AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillation

Qizhe Wei, Yingping Liang, Shaodi You, Ying Fu

Learning-based stereo matching models struggle in underwater environments due to scarce in-domain data and the difficulty of extracting discriminative correspondences from degraded imagery. In this work, we present $\textbf{AquaStereo}$, a perception-enhanced framework with a dat…

View free PDFSource page
arxivcs.CVcs.AI2026-07-21

OPD-IAD: From Language Judgment to Industrial Anomaly Detection via On-Policy Self-Distillation

Shuimu Chen, Jing Jin, Nan Su, Hongbo Xu, Zebang Cheng, Wenming Yang, et al.

Large vision-language models (LVLMs) have recently shown strong potential for industrial anomaly detection (IAD) by providing image-level anomaly judgments and interpretable defect reasoning. However, current LVLM-based IAD methods still struggle to produce precise pixel-level an…

View free PDFSource page