paper-with-me

Papers

InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding

2026-04-09 · Ashutosh Kumar, Rajat Saini, Jingjing Pan, Mustafa Erdogan, Mingfang Zhang, Betty Le Dem, Norimasa Kobori, Quan Kong arxiv

Current vision-language pre-training (VLP) paradigms excel at global scene understanding but struggle with instance-level reasoning due to global-only supervision. We introduce InstAP, an Instance-Aware Pre-training framework that jointly optimizes global vision-text alignment and fine-grained, instance-level contrastive alignment by grounding textual mentions to specific spatial-temporal regions. To support this, we present InstVL, a large-scale dataset (2 million images, 50,000 videos) with dual-granularity annotations: holistic scene captions and dense, grounded instance descriptions. On the InstVL benchmark, InstAP substantially outperforms existing VLP models on instance-level retrieval, and also surpasses a strong VLP baseline trained on the exact same data corpus, isolating the benefit of our instance-aware objective. Moreover, instance-centric pre-training improves global understanding: InstAP achieves competitive zero-shot performance on multiple video benchmarks, including MSR-VTT and DiDeMo. Qualitative visualizations further show that InstAP localizes textual mentions to the correct instances, while global-only models exhibit more diffuse, scene-level attention.

📄 PDF Abstract BibTeX arXiv:2604.08337

Code (0)

등록된 구현이 없습니다.

Tasks

Scene Understanding

Similar Papers 제목 키워드 기반

Rethinking Distributional Matching Based Domain Adaptation

2020-06-23 · Bo Li, Yezhen Wang, Tong Che, Shanghang Zhang 외

Domain adaptation (DA) is a technique that transfers predictive models trained on a labeled source domain to an unlabeled target domain, with the core difficulty of resolving distributional shift between domains. Current…

Domain Adaptation

FM-Fusion: Instance-aware Semantic Mapping Boosted by Vision-Language Foundation Models

2024-02-07 · Chuhao Liu, Ke Wang, Jieqi Shi, Zhijian Qiao 외

Semantic mapping based on the supervised object detectors is sensitive to image distribution. In real-world environments, the object detection and segmentation performance can lead to a major drop, preventing the use of …

Instance SegmentationObjectobject-detectionObject Detection+2

IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting

2025-03-26 · Hao Fu, Hanbin Zhao, Jiahua Dong, Chao Zhang 외

Recent pre-trained vision-language models (PT-VLMs) often face a Multi-Domain Class-Incremental Learning (MCIL) scenario in practice, where several classes and domains of multi-modal tasks are incrementally arrived. With…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+1

iMOVE: Instance-Motion-Aware Video Understanding

2025-02-17 · Jiaze Li, Yaya Shi, Zongyang Ma, Haoran Xu 외

Enhancing the fine-grained instance spatiotemporal motion perception capabilities of Video Large Language Models is crucial for improving their temporal and general video understanding. However, current models struggle t…

Computational EfficiencyVideo Understanding

IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model

2024-07-10 · Yatai Ji, Shilong Zhang, Jie Wu, Peize Sun 외

The rapid advancement of Large Vision-Language models (LVLMs) has demonstrated a spectrum of emergent capabilities. Nevertheless, current models only focus on the visual content of a single scenario, while their ability …

Language ModelingLanguage ModellingQuestion Answering