AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Sentence Attention Blocks for Answer Grounding

Seyedalireza Khoshsirat, Chandra Kambhamettu

ICCV 2023 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 7 citations (OpenAlex)

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 changedWhereMeasuredEffect
add LayerNorm normalization layer to the cross-attention block (ablation)Sentence Attention Block · VizWiz-VQA-Grounding valMean IoU: 70.1 -> 71.2Improved
replace sigmoid with softmax (ablation)Sentence Attention Block · VizWiz-VQA-Grounding valMean IoU: 71.2 -> 72.7Improved
invert the bottleneck by expanding embeddings by a factor of two (ablation)Sentence Attention Block · VizWiz-VQA-Grounding valMean IoU: 72.7 -> 73.5Improved
add higher-resolution scales to multi-scale fusion (1/32 to 1/32+1/16+1/8+1/4) (ablation)Sentence Attention Block · VizWiz-VQA-Grounding valMean IoU: 71.4 -> 73.5Improved
use EfficientNet-B7 backbone instead of ResNet-50x3 (ablation)Sentence Attention Block · VizWiz-VQA-Grounding valMean IoU: 71.9 -> 73.5Improved
use Swin Transformer V2-B instead of EfficientNet-B7 (ablation)Sentence Attention Block · VizWiz-VQA-Grounding valMean IoU: 73.5 -> 72.8Hurt
use EfficientNetV2-L instead of EfficientNet-B7 (ablation)Sentence Attention Block · VizWiz-VQA-Grounding valMean IoU: 73.5 -> 73.1Hurt
use MiniLMv2 sentence encoder instead of RoBERTa or MPNet (ablation)Sentence Attention Block · VizWiz-VQA-Grounding valMean IoU: 72.8 / 73.1 -> 73.5Improved
apply Sentence Attention Block vs MAC-Capsanswer grounding · TextVQA-X testMean IoU: 26.1 -> 29.0Improved
apply Sentence Attention Block vs best prior method on VizWiz challengeanswer grounding · VizWiz-VQA-Grounding Challenge 2022Mean IoU: 70.6 -> 72.4Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy