L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training | Paper Citation Record

Observation af9e9b67-ed51-43f0-a289-8f9970342520 · outbound

This paper cites Learning cnn-lstm architectures for image caption generation,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Learning cnn-lstm architectures for image caption generation,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.538709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 98920df9-8da1-4c92-b48d-4e976d93e013 · outbound

This paper cites Image captioning through image transformer,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Image captioning through image transformer,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.528365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2b78848c-363e-4dbb-818d-7779191acc0b · outbound

This paper cites Meshed-memory transformer for image captioning,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Meshed-memory transformer for image captioning,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.517298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 724a695d-4006-446b-b5d5-c6b7680e669c · outbound

This paper cites Bottom-up and top-down attention for image captioning and visual question answering,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Bottom-up and top-down attention for image captioning and visual question answering,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.505011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3a749b07-904b-437b-a0b3-6be7fa4d1177 · outbound

This paper cites Self- critical sequence training for image captioning,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Self- critical sequence training for image captioning,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:45.008929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21ca654c-8798-4748-ae07-cac4c4654afa · outbound

This paper cites Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image cap- tioning,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image cap- tioning,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.482559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6233736e-00d0-45bb-a043-a7cba9c56470 · outbound

This paper cites Microsoft coco: Common objects in context,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Microsoft coco: Common objects in context,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:45.215989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fe3c809-e63e-4f17-ae2a-7ed19de952a0 · outbound

This paper cites Bleu: a method for automatic evaluation of machine translation,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Bleu: a method for automatic evaluation of machine translation,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:45.325805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7189918-21d6-4020-a0d7-b828d7412d6d · outbound

This paper cites Cider: Consensus- based image description evaluation,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Cider: Consensus- based image description evaluation,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:45.401247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a1376e0-81c8-435b-9c09-1c69de0c4497 · outbound

This paper cites Bertscore: Evaluating text generation with bert,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Bertscore: Evaluating text generation with bert,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.451864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 196d3fa2-6bb0-4897-a325-0db460aa2a3f · outbound

This paper cites What you see is what you read? improv- ing text-image alignment evaluation,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training What you see is what you read? improv- ing text-image alignment evaluation,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.442462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 738d87d5-2d8d-40ca-a429-d349426f4e66 · outbound

This paper cites Fast, accurate, and lightweight memory-enhanced embedding learning framework for image-text retrieval,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Fast, accurate, and lightweight memory-enhanced embedding learning framework for image-text retrieval,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.432955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 34fd9183-3893-4f64-bb97-884567a1abe8 · outbound

This paper cites Vilbertscore: Evaluating image caption using vision-and-language bert,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Vilbertscore: Evaluating image caption using vision-and-language bert,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.421682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 16462428-c0fa-474d-a16c-51ad33ce8d5e · outbound

This paper cites Image-text alignment and retrieval using light-weight transformer,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Image-text alignment and retrieval using light-weight transformer,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.396031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b86d9278-ae41-4bd3-929a-1f025224a9f0 · outbound

This paper cites UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:45.987661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b11e06f7-676b-404a-b3d5-0d11a036e1a1 · outbound

This paper cites Less is more: Clipbert for video-and-language learning via sparse sampling,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Less is more: Clipbert for video-and-language learning via sparse sampling,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.382031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 523b857d-58f0-4d9e-94a8-81e3b919172a · outbound

This paper cites Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.369989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 10672b9f-a868-466f-8a6c-b1c479216c38 · outbound

This paper cites Quality estimation for image captions based on large-scale human evaluations,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Quality estimation for image captions based on large-scale human evaluations,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.346489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 067683fa-cef1-4c83-811c-27ee9be55865 · outbound

This paper cites Revealing the dark secrets of bert,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Revealing the dark secrets of bert,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.328710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 104ac830-39ae-4fed-9f7f-ce993210402d · outbound

This paper cites Minivit: Compressing vision transformers with weight multiplexing,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Minivit: Compressing vision transformers with weight multiplexing,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.318090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8ad54b67-70ec-4ebe-9c0d-6cd9ca908c74 · outbound

This paper cites ALBERT: A Lite BERT for Self-supervised Learning of Language Representations.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:46.607900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee9aa492-63a3-4d64-b84b-55e70a95c154 · outbound

This paper cites Enabling multimodal generation on clip via vision-language knowledge distilla- tion,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Enabling multimodal generation on clip via vision-language knowledge distilla- tion,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.291873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 65ec115c-e93a-478d-a9bb-c43a8a8ca597 · outbound

This paper cites CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:46.816291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60ba08d4-fc9b-4506-a040-d906a169dae3 · outbound

This paper cites Learning transferable visual models from natural language supervision,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Learning transferable visual models from natural language supervision,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:46.902472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0f769db-72fa-4407-b8cd-bcbe1e6ffbd3 · outbound

This paper cites Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.226808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 571e6b59-0e11-4213-bfca-acffcc3b3899 · outbound

This paper cites Knowing when to look: Adaptive attention via a visual sentinel for image captioning,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Knowing when to look: Adaptive attention via a visual sentinel for image captioning,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:19:58.182859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c435e904-4efc-468e-90e1-77a151c923e6 · outbound

This paper cites Know more say less: Image captioning based on scene graphs,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Know more say less: Image captioning based on scene graphs,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:57.441150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9192a4e7-23b4-4c75-aad3-0e2a41fc051a · outbound

This paper cites High-quality image cap- tioning with fine-grained and semantic-guided visual attention,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training High-quality image cap- tioning with fine-grained and semantic-guided visual attention,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:57.142395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 45cf7118-9da8-4cb3-b021-9ce38f332a1e · outbound

This paper cites Multimodal transformer with multi- view visual representation for image captioning,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Multimodal transformer with multi- view visual representation for image captioning,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:56.954306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9dbb5512-162e-4619-b482-2081258a674a · outbound

This paper cites Compact bidirectional transformer for image captioning,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Compact bidirectional transformer for image captioning,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:56.756704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 58c688ad-e4fc-45fb-a40f-f41e3ad78348 · outbound

This paper cites Task-adaptive attention for image captioning,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Task-adaptive attention for image captioning,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:56.571741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b8faab56-4325-4121-a7fa-e0fc61873d7c · outbound

This paper cites Textual context-aware dense captioning with diverse words,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Textual context-aware dense captioning with diverse words,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:56.262369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 46457da1-e0aa-4070-8373-e2adfac91838 · outbound

This paper cites Meteor: An automatic metric for mt evalua- tion with improved correlation with human judgments,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Meteor: An automatic metric for mt evalua- tion with improved correlation with human judgments,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:47.800623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5722b42-588b-466a-be6c-900b74189f3e · outbound

This paper cites Rouge: A package for automatic evaluation of summaries,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Rouge: A package for automatic evaluation of summaries,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:47.891704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b440dc69-0d02-42c1-a27d-3735867b32a8 · outbound

This paper cites Spice: Semantic propositional image caption evaluation,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Spice: Semantic propositional image caption evaluation,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:47.956604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9266a018-e0eb-40f0-a5ec-d9b3eb341cf1 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:48.077301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac99a651-3121-4d31-8668-a42d84296387 · outbound

This paper cites Clipscore: A reference-free evaluation metric for image captioning,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Clipscore: A reference-free evaluation metric for image captioning,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:55.989883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9e56f2de-0a44-46f0-8363-b3366ecad143 · outbound

This paper cites Tiger: Text-to-image grounding for image caption evalua- tion,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Tiger: Text-to-image grounding for image caption evalua- tion,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:55.753289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 473024b0-5264-48ed-91fa-011520487af3 · outbound

This paper cites Em- score: Evaluating video captioning via coarse-grained and fine-grained embedding matching,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Em- score: Evaluating video captioning via coarse-grained and fine-grained embedding matching,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:55.505044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2bebff7b-075d-4dc3-9477-81a543bc9c20 · outbound

This paper cites Gpt-3: Its nature, scope, limits, and consequences,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Gpt-3: Its nature, scope, limits, and consequences,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:48.555233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e0d5cf6-ec6d-4216-9234-d04b0fb41152 · outbound

This paper cites Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehen- sion,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehen- sion,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:55.274386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1b91fbc6-9386-456e-9543-9953ab43f225 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Swin transformer: Hierarchical vision transformer using shifted windows,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:48.724702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f07502a-6d12-430e-8cbe-bf26a807362b · outbound

This paper cites Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:48.992310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4c820e8-97fb-4d58-8dae-ad870c5dcfc1 · outbound

This paper cites VL-BERT: Pre-training of Generic Visual-Linguistic Representations.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training VL-BERT: Pre-training of Generic Visual-Linguistic Representations

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:49.108576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 671a853a-d350-4185-a7bd-c000fcfee516 · outbound

This paper cites Slip: Self-supervision meets language-image pre-training,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Slip: Self-supervision meets language-image pre-training,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:54.996841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d5a17254-2f11-44e3-be44-f90bd97b8975 · outbound

This paper cites Pruning Filters for Efficient ConvNets.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Pruning Filters for Efficient ConvNets

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:49.439407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ede5327c-922a-4ed8-9555-cb7fb26c0b0c · outbound

This paper cites Vision Transformer Pruning.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Vision Transformer Pruning

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:49.586224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df4b184b-157f-4be5-a4cf-3c00dbcc0f2f · outbound

This paper cites Post-training quantization for vision transformer,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Post-training quantization for vision transformer,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:54.652256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0505ab65-2ef6-496c-98ae-c4ec38866818 · outbound

This paper cites Tinyvit: Fast pretraining distillation for small vision transformers,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Tinyvit: Fast pretraining distillation for small vision transformers,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:54.444617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0b0011c6-d04c-4753-abb2-3a5bdf78d27f · outbound

This paper cites Tinybert: Distilling bert for natural language understanding,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Tinybert: Distilling bert for natural language understanding,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:54.259692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2b89c3d1-403f-4093-b9d5-8456c1de0eb0 · outbound

This paper cites DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:50.162524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b39e71e5-76e7-4887-a9a7-cdab83f87c18 · outbound

This paper cites Training data-efficient image transformers & distillation through attention,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Training data-efficient image transformers & distillation through attention,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:50.303885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57e846a7-95fc-4f08-b549-f0006eaa6703 · outbound

This paper cites Attention is all you need,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Attention is all you need,

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:50.460291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 507da7cf-40af-4f7e-b50a-a3421316f702 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:50.608287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b05c5f1-1756-47bf-91a4-56717f2c1ae2 · outbound

This paper cites Bag of tricks for image classification with convolutional neural networks,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Bag of tricks for image classification with convolutional neural networks,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:54.104734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4af3bb92-6134-416d-b4aa-62c6937a5550 · outbound

This paper cites Making convolutional networks shift-invariant again,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Making convolutional networks shift-invariant again,

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:53.800069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 20d691ff-b298-4771-935b-70f04e205385 · outbound

This paper cites Discriminability objective for training descriptive captions,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Discriminability objective for training descriptive captions,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:53.570868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 07f51bdc-c850-49b2-81e8-fb98b53f422f · outbound

This paper cites ImageNet Large Scale Visual Recognition Challenge,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training ImageNet Large Scale Visual Recognition Challenge,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:51.056134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ba5db4d-d95c-41f0-a492-b0611a25abff · outbound

This paper cites Framing image description as a ranking task: Data, models and evaluation metrics,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Framing image description as a ranking task: Data, models and evaluation metrics,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:53.266631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fa8cb4f5-4a9b-4e46-b2d8-af3aa3151a8b · outbound

This paper cites From Images to Sentences through Scene Description Graphs using Commonsense Reasoning and Knowledge.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training From Images to Sentences through Scene Description Graphs using Commonsense Reasoning and Knowledge

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:51.241514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5ca7f10-23d0-4445-9220-275089ddd46e · outbound

This paper cites Consensus-based image description evaluation,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Consensus-based image description evaluation,

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:53.042948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0433243b-fd85-4fcc-af24-11e652ff5144 · outbound

This paper cites Foil it! find one mismatch between image and language caption,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Foil it! find one mismatch between image and language caption,

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:52.700175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6705d649-e7d7-4e3f-9634-a4129066491c · outbound

This paper cites Deep visual-semantic alignments for gen- erating image descriptions,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Deep visual-semantic alignments for gen- erating image descriptions,

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:52.538573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 24f8f060-4a72-4d69-a4fb-4b7d196df7b4 · outbound

This paper cites Vinvl: Revisiting visual representations in vision-language models,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Vinvl: Revisiting visual representations in vision-language models,

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:52.392262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8dd056fb-e566-42b9-a6c3-2a426bbf0ca9 · outbound

This paper cites Adam: A method for stochastic optimization,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Adam: A method for stochastic optimization,

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:52.258827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fc4aa0b8-2168-462a-8dd9-58111a0fc563 · outbound

This paper cites Improving image captioning evaluation by considering inter references variance,.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Improving image captioning evaluation by considering inter references variance,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:18:52.129394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 380b0f08-6362-4ce7-8203-5776db952ae8 · outbound

This paper cites Concrete Problems in AI Safety.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Concrete Problems in AI Safety

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:51.809319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61a01979-bf04-494a-9ff6-eac046908ce5 · outbound

This paper cites Spontaneous Reward Hacking in Iterative Self-Refinement.

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training Spontaneous Reward Hacking in Iterative Self-Refinement

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T18:18:51.876640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers