Related papers: Ambiguity-Aware and High-Order Relation Learning f…
Deep neural networks often learn and rely on spurious correlations, i.e., superficial associations between non-causal features and the targets. For instance, an image classifier may identify camels based on the desert backgrounds. While it…
Recent advances in large-scale vision and language models have led to significant progress in zero-shot learning tasks. Methods such as CoOp and CoCoOp have shown that replacing handcrafted prompts with learnable vectors, known as prompt…
With the rapid advancement of text-to-image (T2I) generation models, assessing the semantic alignment between generated images and text descriptions has become a significant research challenge. Current methods, including those based on…
We propose TimeHUT, a novel method for learning time-series representations by hierarchical uniformity-tolerance balancing of contrastive representations. Our method uses two distinct losses to learn strong representations with the aim of…
Aligning structured data is a fundamental problem in computer vision and machine learning, underlying tasks such as time series analysis, human action recognition, and visual representation learning. Existing alignment methods, including…
Learning visual semantic similarity is a critical challenge in bridging the gap between images and texts. However, there exist inherent variations between vision and language data, such as information density, i.e., images can contain…
Most existing metric learning methods focus on learning a similarity or distance measure relying on similar and dissimilar relations between sample pairs. However, pairs of samples cannot be simply identified as similar or dissimilar in…
Fine-grained text to image synthesis involves generating images from texts that belong to different categories. In contrast to general text to image synthesis, in fine-grained synthesis there is high similarity between images of different…
Similarity-preserving hashing is a commonly used method for nearest neighbour search in large-scale image retrieval. For image retrieval, deep-networks-based hashing methods are appealing since they can simultaneously learn effective image…
Recently, a multitude of methods for image-to-image translation have demonstrated impressive results on problems such as multi-domain or multi-attribute transfer. The vast majority of such works leverages the strengths of adversarial…
The development of unsupervised hashing is advanced by the recent popular contrastive learning paradigm. However, previous contrastive learning-based works have been hampered by (1) insufficient data similarity mining based on global-only…
In the domain of moment retrieval, accurately identifying temporal segments within videos based on natural language queries remains challenging. Traditional methods often employ pre-trained models that struggle with fine-grained information…
Finding a template in a search image is one of the core problems many computer vision, such as semantic image semantic, image-to-GPS verification \etc. We propose a novel quality-aware template matching method, QATM, which is not only used…
Metaphors play a significant role in our everyday communication, yet detecting them presents a challenge. Traditional methods often struggle with improper application of language rules and a tendency to overlook data sparsity. To address…
Context-aware processing mechanisms have increasingly become a critical area of exploration for improving the semantic and contextual capabilities of language generation models. The Context-Aware Semantic Recomposition Mechanism (CASRM) was…
We present ASAP, a new framework for detecting and grounding multi-modal media manipulation (DGM4).Upon thorough examination, we observe that accurate fine-grained cross-modal semantic alignment between the image and text is vital for…
Current artificial intelligence systems exhibit a fundamental architectural limitation: they resolve ambiguity prematurely. This premature semantic collapse--collapsing multiple valid interpretations into single outputs--stems from…
Text-image alignment constitutes a foundational challenge in multimedia content understanding, where effective modeling of cross-modal semantic correspondences critically enhances retrieval system performance through joint embedding space…
It is well known that humans can learn and recognize objects effectively from several limited image samples. However, learning from just a few images is still a tremendous challenge for existing main-stream deep neural networks. Inspired by…
Contrastive learning has been shown to produce generalizable representations of audio and visual data by maximizing the lower bound on the mutual information (MI) between different views of an instance. However, obtaining a tight lower…