Papers with pretrained VLMs
Predicate Debiasing in Vision-Language Models Integration for Scene Graph Generation Enhancement (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing researches in Scene Graph Generation (SGG) focus on refining model architectures that are trained from scratch with datasets like Visual Genome or Open Images. |
| Approach: | They propose to integrate pretrained Vision-language Models into SGG to improve representation by estimating the unattainable predicates distribution. |
| Outcome: | The proposed method significantly improves the performance of the debiased VLMs with SGG models. |
3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Vision-Language Models (VLMs) have shown remarkable performance on diverse visual and linguistic tasks, yet they remain limited in their understanding of 3D spatial structures. |
| Approach: | They propose a framework that injects human-inspired geometric cues into pretrained VLMs . they use sparse correspondences, relative depth relations and dense cost volumes . |
| Outcome: | The proposed framework outperforms existing methods on vision-language reasoning and 3D perception benchmarks. |