InstAP introduces instance-aware pre-training with a new dual-granularity dataset InstVL that improves both fine-grained instance retrieval and global video understanding over standard VLP baselines.
Multi-grained vi- sion language pre-training: Aligning texts with visual con- cepts
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
WikiCLIP delivers an efficient contrastive baseline for open-domain visual entity recognition that improves accuracy by 16% on OVEN unseen entities and runs nearly 100 times faster than leading generative models.
Stitch-a-Demo is a retrieval-based method that assembles visually coherent video demonstrations from multistep textual descriptions by training on weakly supervised procedural data with hard negatives.
CompART adds a composition loss on decomposed captions to regularize attention sums and improves multi-object grounding plus VQA across four VLM types and six benchmarks.
ViperGPT generates executable Python code to compose pre-trained vision-and-language modules into programs that answer visual queries, reaching state-of-the-art results with no additional training.
LURE reduces object hallucination in LVLMs by 23% via post-hoc revision informed by co-occurrence, uncertainty, and text position analysis.
citing papers explorer
-
InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding
InstAP introduces instance-aware pre-training with a new dual-granularity dataset InstVL that improves both fine-grained instance retrieval and global video understanding over standard VLP baselines.
-
WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition
WikiCLIP delivers an efficient contrastive baseline for open-domain visual entity recognition that improves accuracy by 16% on OVEN unseen entities and runs nearly 100 times faster than leading generative models.
-
Stitch-a-Demo: Video Demonstrations from Multistep Descriptions
Stitch-a-Demo is a retrieval-based method that assembles visually coherent video demonstrations from multistep textual descriptions by training on weakly supervised procedural data with hard negatives.
-
The ART of Composition: Attention-Regularized Training for Compositional Visual Grounding
CompART adds a composition loss on decomposed captions to regularize attention sums and improves multi-object grounding plus VQA across four VLM types and six benchmarks.
-
ViperGPT: Visual Inference via Python Execution for Reasoning
ViperGPT generates executable Python code to compose pre-trained vision-and-language modules into programs that answer visual queries, reaching state-of-the-art results with no additional training.
-
Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
LURE reduces object hallucination in LVLMs by 23% via post-hoc revision informed by co-occurrence, uncertainty, and text position analysis.