Research map / Vision-language and multimodal / Human and embodied modeling
Explainable Semantic Space by Grounding Language to Vision with Cross-Modal Contrastive Learning
Yizhen Zhang, Minkyu Choi, Kuan Han, Zhongming Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add self-attention to the visual stream | VGG-based visual stream · ImageNet validation | top-1 accuracy: 71.6% -> 74.3% | Improved |
| ground language representations in vision | Bert language representations · Human-rated concreteness, word categories | Pearson's r: 0.3538 -> 0.8749 | Improved |
| ground language representations in vision | Bert language representations · Human-rated concreteness, individual words | Pearson's r: 0.1040 -> 0.6615 | Improved |
| also ground object relations | Grounded language representations · Human-rated concreteness, word categories | Pearson's r: 0.8749 -> 0.8001 | Hurt |
| also ground object relations | Grounded language representations · Human-rated concreteness, individual words | Pearson's r: 0.6615 -> 0.6948 | Improved |
| ground language representations in vision | Bert language representations · striped horse → zebra | cosine similarity: 0.12 -> 0.60 | Improved |
| also ground object relations | Grounded language representations · striped horse → zebra | cosine similarity: 0.60 -> 0.63 | Improved |
| ground language representations in vision | Bert language representations · black and white bear → panda | cosine similarity: 0.13 -> 0.69 | Improved |
| ground language representations in vision | Bert language representations · red fruit → strawberry | cosine similarity: 0.39 -> 0.75 | Improved |
| ground language representations in vision | Bert language representations · young dog → puppy | cosine similarity: 0.40 -> 0.92 | Improved |
| fine-tune more of the higher Bert layers during image-text grounding (ablation) | Bert language stream · MS COCO image-text retrieval | image-text retrieval performance | Improved |
Closest papers by meaning
- Bridging Vision and Language Spaces with Assignment Prediction (ICLR 2024 · similarity 0.89)
- GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation (CVPR 2026 · similarity 0.89)
- Bridging the gap to real-world language-grounded visual concept learning (NeurIPS 2025 · similarity 0.88)
- Language Model as Visual Explainer (NeurIPS 2024 · similarity 0.88)
- Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning (AAAI 2026 · similarity 0.88)
- Look Around Before Locating: Considering Content and Structure Information for Visual Grounding (AAAI 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
