Related papers: SAMJAM: Zero-Shot Video Scene Graph Generation for…
Despite tremendous recent progress, generative video models still struggle to capture real-world motion, dynamics, and physics. We show that this limitation arises from the conventional pixel reconstruction objective, which biases models…
Video Foundation Models (VFMs) exhibit remarkable visual generation performance, but struggle in compositional scenarios (e.g., motion, numeracy, and spatial relation). In this work, we introduce Test-Time Optimization and Memorization…
The Segment Anything Model (SAM) is a deep neural network foundational model designed to perform instance segmentation which has gained significant popularity given its zero-shot segmentation ability. SAM operates by generating masks based…
Efficient video-language modeling should consider the computational cost because of a large, sometimes intractable, number of video frames. Parametric approaches such as the attention mechanism may not be ideal since its computational cost…
The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prompt engineering. Segment-Anything(SAM), among others, is the…
Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. It requires not only a comprehensive understanding of each object scattered on the whole scene but also a deep…
In medical image segmentation, heterogeneous privacy policies across institutions often make joint training on pooled datasets infeasible, motivating continual image segmentation-learning from data streams without catastrophic forgetting.…
We propose a novel memory module for building video generators capable of interactively exploring environments. Previous approaches have achieved similar results either by out-painting 2D views of a scene while incrementally reconstructing…
The Segment Anything Model (SAM) has established itself as a powerful zero-shot image segmentation model, enabled by efficient point-centric annotation and prompt-based models. While click and brush interactions are both well explored in…
Zero-shot learning for visual recognition, e.g., object and action recognition, has recently attracted a lot of attention. However, it still remains challenging in bridging the semantic gap between visual features and their underlying…
Image matching is a fundamental computer vision problem. While learning-based methods achieve state-of-the-art performance on existing benchmarks, they generalize poorly to in-the-wild images. Such methods typically need to train separate…
We explore how reconciling several foundation models (large language models and vision-language models) with a novel unified memory mechanism could tackle the challenging video understanding problem, especially capturing the long-term…
Zero-shot video moment retrieval (ZVMR) is the task of localizing a temporal moment within an untrimmed video using a natural language query without relying on task-specific training data. The primary challenge in this setting lies in the…
Cross-view object correspondence, exemplified by the representative task of ego-exo object correspondence, aims to establish consistent associations of the same object across different viewpoints (e.g., egocentric and exocentric). This task…
We present SLIP (SAM+CLIP), an enhanced architecture for zero-shot object segmentation. SLIP combines the Segment Anything Model (SAM) \cite{kirillov2023segment} with the Contrastive Language-Image Pretraining (CLIP)…
The assumption of a static environment is common in many geometric computer vision tasks like SLAM but limits their applicability in highly dynamic scenes. Since these tasks rely on identifying point correspondences between input images…
Scene graphs provide valuable information to many downstream tasks. Many scene graph generation (SGG) models solely use the limited annotated relation triples for training, leading to their underperformance on low-shot (few and zero)…
Scene understanding and reasoning has been a fundamental problem in 3D computer vision, requiring models to identify objects, their properties, and spatial or comparative relationships among the objects. Existing approaches enable this by…
Situational Graphs (S-Graphs) merge geometric models of the environment generated by Simultaneous Localization and Mapping (SLAM) approaches with 3D scene graphs into a multi-layered jointly optimizable factor graph. As an advantage,…
Video generation requires modeling a vast spatiotemporal space, which demands significant computational resources and data usage. To reduce the complexity, the prevailing approaches employ a cascaded architecture to avoid direct training…