Sam 2: Segment anything in images and videos
We present Segment Anything Model 2 (SAM 2), a foundation model towards solving
promptable visual segmentation in images and videos. We build a data engine, which …
promptable visual segmentation in images and videos. We build a data engine, which …
Integrating boxes and masks: A multi-object framework for unified visual tracking and segmentation
Tracking any given object (s) spatially and temporally is a common purpose in Visual Object
Tracking (VOT) and Video Object Segmentation (VOS). Joint tracking and segmentation …
Tracking (VOT) and Video Object Segmentation (VOS). Joint tracking and segmentation …
Omg-llava: Bridging image-level, object-level, pixel-level reasoning and understanding
Current universal segmentation methods demonstrate strong capabilities in pixel-level
image and video understanding. However, they lack reasoning abilities and cannot be …
image and video understanding. However, they lack reasoning abilities and cannot be …
Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation
Open-Vocabulary Video Instance Segmentation (VIS) is attracting increasing attention due
to its ability to segment and track arbitrary objects. However, the recent Open-Vocabulary …
to its ability to segment and track arbitrary objects. However, the recent Open-Vocabulary …
Cold SegDiffusion: A novel diffusion model for medical image segmentation
Medical image segmentation is crucial in accurately identifying and delineating regions of
interest in medical images, which can inform the diagnosis and treatment of various …
interest in medical images, which can inform the diagnosis and treatment of various …
StAlK: Structural Alignment based Self Knowledge distillation for Medical Image Classification
S Sharma, A Kumar, J Monpara, J Chandra - Knowledge-Based Systems, 2024 - Elsevier
In the realm of medical image analysis, where challenges like high class imbalance, inter-
class similarity, and intra-class variance are prevalent, knowledge distillation has emerged …
class similarity, and intra-class variance are prevalent, knowledge distillation has emerged …
VPE-WSVAD: Visual prompt exemplars for weakly-supervised video anomaly detection
Y Su, Y Tan, M Xing, S An - Knowledge-Based Systems, 2024 - Elsevier
Abstract Weakly Supervised Video Anomaly Detection (WSVAD) plays a crucial role in
visual surveillance by effectively distinguishing anomalies from normality with only video …
visual surveillance by effectively distinguishing anomalies from normality with only video …
Temporo-Spatial Parallel Sparse Memory Networks for Efficient Video Object Segmentation
Memory-based networks have achieved tremendous success in video object segmentation.
However, these methods still suffer from unfaithful segmentation and inferior efficiency under …
However, these methods still suffer from unfaithful segmentation and inferior efficiency under …
1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation
Motion Expression guided Video Segmentation (MeViS), as an emerging task, poses many
new challenges to the field of referring video object segmentation (RVOS). In this technical …
new challenges to the field of referring video object segmentation (RVOS). In this technical …
Noise-Tolerant Hybrid Prototypical Learning with Noisy Web Data
We focus on the challenging problem of learning an unbiased classifier from a large number
of potentially relevant but noisily labeled web images given only a few clean labeled …
of potentially relevant but noisily labeled web images given only a few clean labeled …