相关论文: VESSA: Video-based objEct-centric Self-Supervised …

Unsupervised video-based object-centric learning is a promising avenue to learn structured representations from large, unlabeled video collections, but previous approaches have only managed to scale to real-world datasets in restricted…

Existing video-based action recognition systems typically require dense annotation and struggle in environments when there is significant distribution shift relative to the training data. Current methods for video domain adaptation…

Fully supervised Video Semantic Segmentation (VSS) relies heavily on densely annotated video data, limiting practical applicability. Alternatively, applying pre-trained Image Semantic Segmentation (ISS) models frame-by-frame avoids…

State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic pretraining for obtaining good performance on a variety of downstream tasks. Generally, such models are often either cross-modal (contrastive) or…

Current top-leading solutions for video object segmentation (VOS) typically follow a matching-based regime: for each query frame, the segmentation mask is inferred according to its correspondence to previously processed and the first…

Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years. Whereas such task is typically addressed with a domain-specific solution focused on natural images, we…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Weakly-Supervised Video Anomaly Detection aims to identify anomalous events using only video-level labels, balancing annotation efficiency with practical applicability. However, existing methods often oversimplify the anomaly space by…

Vision-language models (VLMs) exhibit remarkable zero-shot generalization but suffer performance degradation under distribution shifts in downstream tasks, particularly in the absence of labeled data. Test-Time Adaptation (TTA) addresses…

The vision transformer-based foundation models, such as ViT or Dino-V2, are aimed at solving problems with little or no finetuning of features. Using a setting of prototypical networks, we analyse to what extent such foundation models can…

Despite significant progress in semi-supervised learning for image object detection, several key issues are yet to be addressed for video object detection: (1) Achieving good performance for supervised video object detection greatly depends…

Large Vision-Language Models (LVLMs) have experienced significant advancements in recent years. However, their performance still falls short in tasks requiring deep visual perception, such as identifying subtle differences between images. A…

Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only tunes a small number of parameters while freezing the vast…

Foundation models have shown outstanding performance and generalization capabilities across domains. Since most studies on foundation models mainly focus on the pretraining phase, a naive strategy to minimize a single task-specific loss is…

Visual reinforcement learning agents typically face serious performance declines in real-world applications caused by visual distractions. Existing methods rely on fine-tuning the policy's representations with hand-crafted augmentations. In…

In computer vision, Visual Prompting (VP) and Visual Prompt Tuning (VPT) have recently emerged as lightweight and effective alternatives to full fine-tuning for adapting large-scale vision models within the "pretrain-then-finetune"…

Weakly supervised visual grounding aims to predict the region in an image that corresponds to a specific linguistic query, where the mapping between the target object and query is unknown in the training stage. The state-of-the-art method…

Foundation models leverage large-scale pretraining to capture extensive knowledge, demonstrating generalization in a wide range of language tasks. By comparison, vision foundation models (VFMs) often exhibit uneven improvements across…

Vision-language object detectors (VLODs) such as YOLO-World and Grounding DINO exhibit strong zero-shot generalization, but their performance degrades under distribution shift. Test-time adaptation (TTA) offers a practical way to adapt…

Unsupervised object-centric learning from videos is a promising approach towards learning compositional representations that can be applied to various downstream tasks, such as prediction and reasoning. Recently, it was shown that…