Text-based Aerial-Ground Person Retrieval

arXiv — cs.CV•Wednesday, November 12, 2025 at 5:00:00 AM

The recent development of Text-based Aerial-Ground Person Retrieval (TAG-PR) represents a notable step forward in the field of image retrieval, particularly in addressing the complexities of retrieving person images from disparate aerial and ground perspectives. This innovation is underscored by the introduction of the TAG-PEDES dataset, which is constructed from public benchmarks and features automatically generated textual descriptions, ensuring robustness against view heterogeneity. Complementing this dataset is the TAG-CLIP retrieval framework, designed to effectively manage the challenges of viewpoint discrepancies through a mixture of experts module that learns both view-specific and view-agnostic features. The effectiveness of TAG-CLIP has been evaluated on the TAG-PEDES dataset as well as existing benchmarks, demonstrating its potential for practical applications. Both the dataset and the code are accessible on GitHub, facilitating further research and development in this area.

— via World Pulse Now AI Editorial System

Read Original

Was this article worth reading? Share it

Recommended Readings

arXiv — cs.CV2 days ago

Bridging Hidden States in Vision-Language Models

PositiveArtificial Intelligence

Vision-Language Models (VLMs) are emerging models that integrate visual content with natural language. Current methods typically fuse data either early in the encoding process or late through pooled embeddings. This paper introduces a lightweight fusion module utilizing cross-only, bidirectional attention layers to align hidden states from both modalities, enhancing understanding while keeping encoders non-causal. The proposed method aims to improve the performance of VLMs by leveraging the inherent structure of visual and textual data.

Read full article

via arXiv — cs.CV

arXiv — cs.LG2 days ago

Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning

PositiveArtificial Intelligence

The paper titled 'Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning' introduces a new method called Bias-REstrained Prefix Representation FineTuning (BREP ReFT). This approach aims to enhance the mathematical reasoning capabilities of models by addressing the limitations of existing Representation finetuning (ReFT) methods, which struggle with mathematical tasks. The study demonstrates that BREP ReFT outperforms both standard ReFT and weight-based Parameter-Efficient finetuning (PEFT) methods through extensive experiments.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Transformers know more than they can tell -- Learning the Collatz sequence

NeutralArtificial Intelligence

The study investigates the ability of transformer models to predict long steps in the Collatz sequence, a complex arithmetic function that maps odd integers to their successors. The accuracy of the models varies significantly depending on the base used for encoding, achieving up to 99.7% accuracy for bases 24 and 32, while dropping to 37% and 25% for bases 11 and 3. Despite these variations, all models exhibit a common learning pattern, accurately predicting inputs with similar residuals modulo 2^p.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions

PositiveArtificial Intelligence

Higher-order Neural Additive Models (HONAMs) have been introduced as an advancement over Neural Additive Models (NAMs), which are known for their predictive performance and interpretability. HONAMs address the limitation of NAMs by effectively capturing feature interactions of arbitrary orders, enhancing predictive accuracy while maintaining interpretability, crucial for high-stakes applications. The source code for HONAM is publicly available on GitHub.

Read full article

via arXiv — cs.LG