Related papers: CAPE: A CLIP-Aware Pointing Ensemble of Complement…

Referring video segmentation relies on natural language expressions to identify and segment objects, often emphasizing motion clues. Previous works treat a sentence as a whole and directly perform identification at the video-level, mixing…

Effectively aligning with human judgment when evaluating machine-generated image captions represents a complex yet intriguing challenge. Existing evaluation metrics like CIDEr or CLIP-Score fall short in this regard as they do not take into…

Audio-visual video parsing is the task of categorizing a video at the segment level with weak labels, and predicting them as audible or visible events. Recent methods for this task leverage the attention mechanism to capture the semantic…

For humans, both the proprioception and touch sensing are highly utilized when performing haptic perception. However, most approaches in robotics use only either proprioceptive data or touch data in haptic object recognition. In this paper,…

We propose a novel unsupervised backlit image enhancement method, abbreviated as CLIP-LIT, by exploring the potential of Contrastive Language-Image Pre-Training (CLIP) for pixel-level image enhancement. We show that the open-world CLIP…

Contrastive Language-Image Pretraining (CLIP) performs zero-shot image classification by mapping images and textual class representation into a shared embedding space, then retrieving the class closest to the image. This work provides a new…

Panoptic tracking enables pixel-level scene interpretation of videos by integrating instance tracking in panoptic segmentation. This provides robots with a spatio-temporal understanding of the environment, an essential attribute for their…

Contrastive Language-Image Pre-training (CLIP) has recently shown great promise in pixel-level zero-shot learning tasks. However, existing approaches utilizing CLIP's text and patch embeddings to generate semantic masks often misidentify…

We present CUPID: a visualization method for the contextual understanding of prompt-conditioned image distributions. CUPID targets the visual analysis of distributions produced by modern text-to-image generative models, wherein a user can…

CLIP is one of the most popular foundational models and is heavily used for many vision-language tasks. However, little is known about the inner workings of CLIP. To bridge this gap we propose a study to quantify the interpretability in…

Significant progress has been made on visual captioning, largely relying on pre-trained features and later fixed object detectors that serve as rich inputs to auto-regressive models. A key limitation of such methods, however, is that the…

Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability. The high generality and usability of these visual models is achieved via a web-scale data collection process to ensure broad concept…

Existing pedestrian attribute recognition (PAR) algorithms adopt pre-trained CNN (e.g., ResNet) as their backbone network for visual feature learning, which might obtain sub-optimal results due to the insufficient employment of the…

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…

Object proposal generation is an important and fundamental task in computer vision. In this paper, we propose ProposalCLIP, a method towards unsupervised open-category object proposal generation. Unlike previous works which require a large…

Contrastive Language-Image Pre-training (CLIP) has shown impressive performance in aligning visual and textual representations. Recent studies have extended this paradigm to 3D vision to improve scene understanding for autonomous driving. A…

People often give instructions whose meaning is ambiguous without further context, expecting that their actions or goals will disambiguate their intentions. How can we build assistive agents that follow such instructions in a flexible,…

In a real-world setting, visual recognition systems can be brought to make predictions for images belonging to previously unknown class labels. In order to make semantically meaningful predictions for such inputs, we propose a two-step…

Tactile data and kinesthetic cues are two important sensing sources in robot object recognition and are complementary to each other. In this paper, we propose a novel algorithm named Iterative Closest Labeled Point (iCLAP) to recognize…

Large-scale vision-language models demonstrate strong multimodal alignment and generalization across diverse tasks. Among them, CLIP stands out as one of the most successful approaches. In this work, we extend the application of CLIP to…