Related papers: WiFi2Cap: Semantic Action Captioning from Wi-Fi CS…
Evaluating visual activity recognition systems is challenging due to inherent ambiguities in verb semantics and image interpretation. When describing actions in images, synonymous verbs can refer to the same event (e.g., brushing vs.…
Referring image segmentation aims to segment a referent via a natural linguistic expression.Due to the distinct data properties between text and image, it is challenging for a network to well align text and pixel-level features. Existing…
In this paper, we demonstrate that CLIP can also be adapted to downstream tasks where its vision-language alignment is suboptimally learned during pre-training on web-crawled data, all without requiring fine-tuning. We explore the case of…
Visual recognition in a low-data regime is challenging and often prone to overfitting. To mitigate this issue, several data augmentation strategies have been proposed. However, standard transformations, e.g., rotation, cropping, and…
Video captioning aims to generate comprehensive and coherent descriptions of the video content, contributing to the advancement of both video understanding and generation. However, existing methods often suffer from motion-detail imbalance,…
Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…
In recent years, language-guided open-set aerial object detection has gained significant attention due to its better alignment with real-world application needs. However, due to limited datasets, most existing language-guided methods…
Creating a virtual avatar with semantically coherent gestures that are aligned with speech is a challenging task. Existing gesture generation research mainly focused on generating rhythmic beat gestures, neglecting the semantic context of…
Channel state information (CSI) is a fundamental component in both wireless communication and sensing systems, enabling critical functions such as radio resource optimization and environmental perception. In wireless sensing, data scarcity…
Contrastive vision-language models, such as CLIP, have demonstrated excellent zero-shot capability across semantic recognition tasks, mainly attributed to the training on a large-scale I&1T (one Image with one Text) dataset. This kind of…
Adaptation of semantic segmentation networks to different visual conditions is vital for robust perception in autonomous cars and robots. However, previous work has shown that most feature-level adaptation methods, which employ adversarial…
Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building…
Bridging robot action sequences and their natural language captions is an important task to increase explainability of human assisting robots in their recently evolving field. In this paper, we propose a system for generating natural…
Grounding-based vision and language models have been successfully applied to low-level vision tasks, aiming to precisely locate objects referred in captions. The effectiveness of grounding representation learning heavily relies on the scale…
Zero-shot action recognition is challenging due to the semantic gap between seen and unseen classes. We present a novel framework that enhances CLIP with disentangled embeddings and semantic-guided interaction. A Motion Separation Module…
Understanding human actions is critical for advancing behavior analysis in human-robot interaction. Particularly in tasks that demand quick and proactive feedback, robots must recognize human actions as early as possible from incomplete…
Integrated sensing and communication (ISAC) unifies wireless communication and sensing by sharing spectrum and hardware, which often incurs trade-offs between two functions due to limited resources. However, this paper shifts focus to…
Multi-modal learning, particularly among imaging and linguistic modalities, has made amazing strides in many high-level fundamental visual understanding problems, ranging from language grounding to dense event captioning. However, much of…
Caption quality has emerged as a critical bottleneck in training high-quality text-to-image (T2I) and text-to-video (T2V) generative models. While visual language models (VLMs) are commonly deployed to generate captions from visual data,…
In this paper we study a brand new topic of interactive image captioning with human in the loop. Different from automated image captioning where a given test image is the sole input in the inference stage, we have access to both the test…