SOTAVerified

Image Captioning

Image Captioning is the task of describing the content of an image in words. This task lies at the intersection of computer vision and natural language processing. Most image captioning systems use an encoder-decoder framework, where an input image is encoded into an intermediate representation of the information in the image, and then decoded into a descriptive text sequence. The most popular benchmarks are nocaps and COCO, and models are typically evaluated according to a BLEU or CIDER metric.

( Image credit: Reflective Decoding Network for Image Captioning, ICCV'19)

Papers

Showing 110 of 1878 papers

Show:102550
← PrevPage 1 of 188Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1IBM Research AICIDEr80.67Unverified
2CASIA_IVACIDEr79.15Unverified
3feixiangCIDEr77.31Unverified
4wocaoCIDEr77.21Unverified
5lamiwab172CIDEr75.93Unverified
6RUC_AIM3CIDEr73.52Unverified
7funasCIDEr73.51Unverified
8SRC-B_VCLabCIDEr73.47Unverified
9spartaCIDEr73.41Unverified
10x-vizCIDEr73.26Unverified
#ModelMetricClaimedVerifiedStatus
1VALORCIDER152.5Unverified
2VASTCIDER149Unverified
3Virtex (ResNet-101)CIDER94Unverified
4KOSMOS-1 (1.6B) (zero-shot)CIDER84.7Unverified
5BLIP-FuseCapCLIPScore78.5Unverified
6mPLUGBLEU-446.5Unverified
7OFABLEU-444.9Unverified
8GITBLEU-444.1Unverified
9BLIP-2 ViT-G OPT 2.7B (zero-shot)BLEU-443.7Unverified
10BLIP-2 ViT-G OPT 6.7B (zero-shot)BLEU-443.5Unverified
#ModelMetricClaimedVerifiedStatus
1PaLICIDEr149.1Unverified
2GIT2, Single ModelCIDEr124.18Unverified
3GIT, Single ModelCIDEr122.4Unverified
4PaLICIDEr121.09Unverified
5CoCa - Google BrainCIDEr117.9Unverified
6Microsoft Cognitive Services teamCIDEr112.82Unverified
7Single ModelCIDEr108.98Unverified
8GRIT (zero-shot, no VL pretraining, no CBS)CIDEr105.9Unverified
9FudanFVLCIDEr104.9Unverified
10FudanWYZCIDEr104.25Unverified
#ModelMetricClaimedVerifiedStatus
1GIT2, Single ModelCIDEr125.51Unverified
2PaLICIDEr124.35Unverified
3GIT, Single ModelCIDEr123.92Unverified
4CoCa - Google BrainCIDEr120.73Unverified
5Microsoft Cognitive Services teamCIDEr115.54Unverified
6Single ModelCIDEr110.76Unverified
7FudanFVLCIDEr109.33Unverified
8FudanWYZCIDEr108.04Unverified
9IEDA-LABCIDEr100.15Unverified
10firetheholeCIDEr99.51Unverified
#ModelMetricClaimedVerifiedStatus
1PaLICIDEr126.67Unverified
2GIT2, Single ModelCIDEr122.27Unverified
3GIT, Single ModelCIDEr122.04Unverified
4CoCa - Google BrainCIDEr121.69Unverified
5Microsoft Cognitive Services teamCIDEr110.14Unverified
6Single ModelCIDEr109.49Unverified
7FudanFVLCIDEr106.55Unverified
8FudanWYZCIDEr103.75Unverified
9HumanCIDEr91.62Unverified
10firetheholeCIDEr88.54Unverified