Related papers: PD-APE: A Parallel Decoding Framework with Adaptiv…
Spatio-temporal video grounding aims to retrieve the spatio-temporal tube of a queried object according to the given sentence. Currently, most existing grounding methods are restricted to well-aligned segment-sentence pairs. In this paper,…
Every autonomous driving dataset has a different configuration of sensors, originating from distinct geographic regions and covering various scenarios. As a result, 3D detectors tend to overfit the datasets they are trained on. This causes…
Visual Grounding (VG) aims to locate the most relevant region in an image, based on a flexible natural language query but not a pre-defined label, thus it can be a more useful technique than object detection in practice. Most…
A hallmark of the deep learning era for computer vision is the successful use of large-scale labeled datasets to train feature representations for tasks ranging from object recognition and semantic segmentation to optical flow estimation…
Positional encodings are essential to transformer-based generative models, yet their behavior in multimodal and attention-sharing settings is not fully understood. In this work, we present a principled analysis of Rotary Positional…
We propose a new 3D spatial understanding task of 3D Question Answering (3D-QA). In the 3D-QA task, models receive visual information from the entire 3D scene of the rich RGB-D indoor scan and answer the given textual questions about the 3D…
Visual localization to compute 6DoF camera pose from a given image has wide applications such as in robotics, virtual reality, augmented reality, etc. Two kinds of descriptors are important for the visual localization. One is global…
Positional encoding plays a pivotal role in determin?ing the extrapolation and generalization performance of wireless foundation models for channel state information (CSI) modeling, latent characterization, and task-specific prediction.…
We present a novel multi-attentional convolutional architecture to tackle the problem of real-time RGB-D 6D object pose tracking of single, known objects. Such a problem poses multiple challenges originating both from the objects' nature…
The introduction of DETR represents a new paradigm for object detection. However, its decoder conducts classification and box localization using shared queries and cross-attention layers, leading to suboptimal results. We observe that…
Human affordance learning investigates contextually relevant novel pose prediction such that the estimated pose represents a valid human action within the scene. While the task is fundamental to machine perception and automated interactive…
Test-time adaptation, which enables models to generalize to diverse data with unlabeled test samples, holds significant value in real-world scenarios. Recently, researchers have applied this setting to advanced pre-trained vision-language…
Vision-and-Language Navigation (VLN) is a challenging task where an agent must understand language instructions and navigate unfamiliar environments using visual cues. The agent must accurately locate the target based on visual information…
We present Multi-View Attentive Contextualization (MvACon), a simple yet effective method for improving 2D-to-3D feature lifting in query-based multi-view 3D (MV3D) object detection. Despite remarkable progress witnessed in the field of…
Visual grounding is the task of locating objects specified by natural language expressions. Existing methods extend generic object detection frameworks to tackle this task. They typically extract visual and textual features separately using…
Given a single scene image, this paper proposes a method of Category-level 6D Object Pose and Size Estimation (COPSE) from the point cloud of the target object, without external real pose-annotated training data. Specifically, beyond the…
3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on textual descriptions, essential for applications like augmented reality and robotics. Traditional 3DVG approaches rely on annotated 3D datasets and predefined object…
Multi-modal 3D object understanding has gained significant attention, yet current approaches often assume complete data availability and rigid alignment across all modalities. We present CrossOver, a novel framework for cross-modal 3D scene…
Accurate depth information is crucial for enhancing the performance of multi-view 3D object detection. Despite the success of some existing multi-view 3D detectors utilizing pixel-wise depth supervision, they overlook two significant…
Positional encoding (PE) underpins how permutation-invariant Transformers represent sequence order, yet how positional information is processed and stored remains poorly understood. Modern PE methods such as RoPE still struggle on tasks…