SOTAVerified

Image Paragraph Captioning

Image paragraph captioning involves generating a detailed, multi-sentence description of the content of an image.

Papers

Showing 11–17 of 17 papers

TitleStatusHype
Recurrent Topic-Transition GAN for Visual Paragraph Generation—0
Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning—0
When an Image Tells a Story: The Role of Visual and Semantic Information for Generating Paragraph Descriptions—0
Bypass Network for Semantics Driven Image Paragraph Captioning—0
Convolutional Auto-encoding of Sentence Topics for Image Paragraph Generation—0
Diverse and Coherent Paragraph Generation from Images—0
Dual-CNN: A Convolutional language decoder for paragraph image captioning—0
Show:102550
← PrevPage 2 of 2Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HSGED(SLL)BLEU-411.26—Unverified
2SCST training, w/ rep. penaltyBLEU-410.58—Unverified
3IMAPBLEU-410.29—Unverified
4CAE-LSTMBLEU-49.67—Unverified
5Diverse and Coherent Paragraph Generation from ImagesBLEU-49.43—Unverified
6RTT-GAN (Semi + Fully)BLEU-49.21—Unverified
7Regions-Hierarchical (ours)BLEU-48.69—Unverified
8Dual-CNNBLEU-48.6—Unverified
9Depth-aware Attention Model (DAM)BLEU-46.7—Unverified
10IMG+LNGBLEU-44.67—Unverified