Videocon: Robust video-language alignment via contrast captions
Despite being (pre) trained on a massive amount of data state-of-the-art video-language
alignment models are not robust to semantically-plausible contrastive changes in the video …
alignment models are not robust to semantically-plausible contrastive changes in the video …
More context, less distraction: Visual classification by inferring and conditioning on contextual attributes
CLIP, as a foundational vision language model, is widely used in zero-shot image
classification due to its ability to understand various visual concepts and natural language …
classification due to its ability to understand various visual concepts and natural language …
Generating Enhanced Negatives for Training Language-Based Object Detectors
The recent progress in language-based open-vocabulary object detection can be largely
attributed to finding better ways of leveraging large-scale data with free-form text …
attributed to finding better ways of leveraging large-scale data with free-form text …
[PDF][PDF] Enhancing Cross-Lingual Image Description: A Multimodal Approach for Semantic Relevance and Stylistic Alignment.
E Al-Buraihy, D Wang - Computers, Materials & Continua, 2024 - cdn.techscience.cn
Cross-lingual image description, the task of generating image captions in a target language
from images and descriptions in a source language, is addressed in this study through a …
from images and descriptions in a source language, is addressed in this study through a …
The crashworthiness prediction and deformation constraint optimization of shrink energy-absorbing structures based on deep learning architecture
J He, P Xu, J Xing, S Yao, B Wang, X Zheng - Advances in Engineering …, 2024 - Elsevier
The deformation behavior of shrink energy-absorbing structures is influenced by numerous
factors, and improper matching of parameters in the design process can easily lead to …
factors, and improper matching of parameters in the design process can easily lead to …
Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection
Vision-language (VL) models often exhibit a limited understanding of complex expressions
of visual objects (eg, attributes, shapes, and their relations), given complex and diverse …
of visual objects (eg, attributes, shapes, and their relations), given complex and diverse …
Evolving Interpretable Visual Classifiers with Large Language Models
Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to
their open-vocabulary flexibility and high performance. However, vision-language models …
their open-vocabulary flexibility and high performance. However, vision-language models …
Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency
Concept bottleneck models (CBMs) have emerged as critical tools in domains where
interpretability is paramount. These models rely on predefined textual descriptions, referred …
interpretability is paramount. These models rely on predefined textual descriptions, referred …
Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort
Enhancing model interpretability can address spurious correlations by revealing how
models draw their predictions. Concept Bottleneck Models (CBMs) can provide a principled …
models draw their predictions. Concept Bottleneck Models (CBMs) can provide a principled …
If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions
Recent works often assume that Vision-Language Model (VLM) representations are based
on visual attributes like shape. However, it is unclear to what extent VLMs prioritize this …
on visual attributes like shape. However, it is unclear to what extent VLMs prioritize this …