Search Results for author:
Found 14 papers, 12 papers with code
TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes
However, the exploration of 3D dense captioning in outdoor scenes is hindered by two major challenges: 1) the \textbf{domain gap} between indoor and outdoor scenes, such as dynamics and sparse visual inputs, makes it difficult to directly adapt existing indoor methods; 2) the \textbf{lack of data} with comprehensive box-caption pair annotations specifically tailored for outdoor scenes.
GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping
In particular, we propose an Efficient Feature Distillation (EFD) module that employs contrastive learning to efficiently and accurately distill language embeddings derived from foundational models.
MonoOcc: Digging into Monocular Semantic Occupancy Prediction
However, existing methods rely on a complex cascaded framework with relatively limited information to restore 3D scenes, including a dependency on supervision solely on the whole network's output, single-frame input, and the utilization of a small backbone.
Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Images
We introduce a novel approach to learn geometries such as depth and surface normal from images while incorporating geometric context.
Improving Data Augmentation for Robust Visual Question Answering with Effective Curriculum Learning
Compared to training on the entire augmented dataset, our ECL strategy can further enhance VQA models' performance with fewer training samples.
3D Implicit Transporter for Temporally Consistent Keypoint Discovery
To address this issue, the Transporter method was introduced for 2D data, which reconstructs the target frame from the source frame to incorporate both spatial and temporal information.
ECT: Fine-grained Edge Detection with Learned Cause Tokens
To address these three issues, we propose a two-stage transformer-based network sequentially predicting generic edges and fine-grained edges, which has a global receptive field thanks to the attention mechanism.
DPF: Learning Dense Prediction Fields with Weak Supervision
We showcase the effectiveness of DPFs using two substantially different tasks: high-level semantic parsing and low-level intrinsic image decomposition.
STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation
By fitting a bridge-shaped curve to the illumination map distribution, both regions are suppressed and two tasks are bridged naturally.
ADAPT: Action-aware Driving Caption Transformer
To bridge the gap, we propose an end-to-end transformer-based architecture, ADAPT (Action-aware Driving cAPtion Transformer), which provides user-friendly natural language narrations and reasoning for each decision making step of autonomous vehicular control and action.
INT2: Interactive Trajectory Prediction at Intersections
One of the most challenging problems in motion forecasting is interactive trajectory prediction, whose goal is to jointly forecasts the future trajectories of interacting agents.
Rethinking Data Augmentation for Robust Visual Question Answering
Unfortunately, to guarantee augmented samples have reasonable ground-truth answers, they manually design a set of heuristic rules for several question types, which extremely limits its generalization abilities.
Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering
Specifically, CSST is composed of two parts: Counterfactual Samples Synthesizing (CSS) and Counterfactual Samples Training (CST).
Sirius: Visualization of Mixed Features as a Mutual Information Network Graph
Data scientists across disciplines are increasingly in need of exploratory analysis tools for data sets with a high volume of features of mixed data type (quantitative continuous and discrete categorical).
