相关论文: DIBS: Enhancing Dense Video Captioning with Unlabe…
Pre-trained vision-language models (VLMs) have enabled significant progress in open vocabulary computer vision tasks such as image classification, object detection and image segmentation. Some recent works have focused on extending VLMs to…
We propose a new "Unbiased through Textual Description (UTD)" video benchmark based on unbiased subsets of existing video classification and retrieval datasets to enable a more robust assessment of video understanding capabilities. Namely,…
In clinical medicine, precise image segmentation can provide substantial support to clinicians. However, obtaining high-quality segmentation typically demands extensive pixel-level annotations, which are labor-intensive and expensive.…
While 3D instance segmentation (3DIS) has advanced significantly, most existing methods assume that all object classes are known in advance and uniformly distributed. However, this assumption is unrealistic in dynamic, real-world…
In recent years, deep dictionary learning (DDL)has attracted a great amount of attention due to its effectiveness for representation learning and visual recognition.~However, most existing methods focus on unsupervised deep dictionary…
An ideal description for a given video should fix its gaze on salient and representative content, which is capable of distinguishing this video from others. However, the distribution of different words is unbalanced in video captioning…
Training neural networks using limited annotations is an important problem in the medical domain. Deep Neural Networks (DNNs) typically require large, annotated datasets to achieve acceptable performance which, in the medical domain, are…
Automatically describing a video with natural language is regarded as a fundamental challenge in computer vision. The problem nevertheless is not trivial especially when a video contains multiple events to be worthy of mention, which often…
We propose a new task and model for dense video object captioning -- detecting, tracking and captioning trajectories of objects in a video. This task unifies spatial and temporal localization in video, whilst also requiring fine-grained…
Learning visual knowledge from massive weakly-labeled web videos has attracted growing research interests thanks to the large corpus of easily accessible video data on the Internet. However, for video action recognition, the action of…
Deep learning has shown remarkable progress in a wide range of problems. However, efficient training of such models requires large-scale datasets, and getting annotations for such datasets can be challenging and costly. In this work, we…
Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding. However, their application to safety-critical driving scenarios remains limited by an inability to…
Image Difference Captioning (IDC) generates natural language descriptions that precisely identify differences between two images, serving as a key benchmark for fine-grained change perception, cross-modal reasoning, and image editing data…
Exploiting unlabeled data through semi-supervised learning (SSL) or leveraging pre-trained models via fine-tuning are two prevailing paradigms for addressing label-scarce scenarios. Recently, growing attention has been given to combining…
Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers trained on such dataset may overfit to these bias attributes,…
Understanding visual differences between dynamic scenes requires the comparative perception of compositional, spatial, and temporal changes--a capability that remains underexplored in existing vision-language systems. While prior work on…
Spread of fake news using out-of-context images and captions has become widespread in this era of information overload. Since fake news can belong to different domains like politics, sports, etc. with their unique characteristics, inference…
For further progress in video object segmentation (VOS), larger, more diverse, and more challenging datasets will be necessary. However, densely labeling every frame with pixel masks does not scale to large datasets. We use a deep…
In recent years, dynamic vision sensors (DVS), also known as event-based cameras or neuromorphic sensors, have seen increased use due to various advantages over conventional frame-based cameras. Using principles inspired by the retina, its…
Unsupervised video class incremental learning (uVCIL) represents an important learning paradigm for learning video information without forgetting, and without considering any data labels. Prior approaches have focused on supervised…