AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Multi-label Instance-level Generalised Visual Grounding in Agriculture

Mohammadreza Haghighat, Alzayat Saleh, Mostafa Azghadi

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 1 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 word-level cues to sentence-level similarity (ablation)Weed-VG · gRef-CW TestTop-1: 49.29 -> 62.42Improved
add sentence-level similarity to word-level cues (ablation)Weed-VG · gRef-CW TestTop-1: 36.19 -> 62.42Improved
add query projection (ablation)Weed-VG · gRef-CW TestTop-1: 33.20 -> 62.42Improved
add query projection (ablation)Weed-VG · gRef-CW TestmIoU: 35.39 -> 57.25Improved
add hierarchical constraint (ablation)Weed-VG · gRef-CW TestNeg-Acc: 41.60 -> 78.35Improved
add hierarchical constraint (ablation)Weed-VG · gRef-CW TestR@0.5: 53.87 -> 55.44No clear effect
add InterpIoU with distance and size aware matching (ablation)Weed-VG · gRef-CW TestmIoU: 47.72 -> 57.25Improved
add InterpIoU with distance and size aware matching (ablation)Weed-VG · gRef-CW TestTop-1: 49.15 -> 62.42Improved
add InterpIoU with distance and size aware matching (ablation)Weed-VG · gRef-CW TestNeg-Acc: 75.88 -> 78.35Improved
wrap GroundingDINO with HRS (Weed-VG) instead of GDINO-L aloneGroundingDINO · gRef-CW TestTop-1: 20.38 -> 62.42Improved
use Weed-VG instead of SAM3 on dense crop scenes (>30 instances)Weed-VG · gRef-CW Test, crop >30 instancesmIoU: 25.81 -> 47.58Improved
use Weed-VG with GDINO-L on large cropsWeed-VG · gRef-CW Test, large cropsTop-1: 74.33 -> 71.90Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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