Search Results for author:
Found 15 papers, 12 papers with code
Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception
With the success of image generation, generative diffusion models are increasingly adopted for discriminative tasks, as pixel generation provides a unified perception interface.
AgMMU: A Comprehensive Agricultural Multimodal Understanding and Reasoning Benchmark
We curate a dataset AgMMU for evaluating and developing vision-language models (VLMs) to produce factually accurate answers for knowledge-intensive expert domains.
GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation
This paper proposes a novel framework utilizing multi-modal large language models (MLLMs) for referring video object segmentation (RefVOS).
Ranked #3 on
Referring Video Object Segmentation
on MeViS
RandAR: Decoder-only Autoregressive Visual Generation in Random Orders
We introduce RandAR, a decoder-only visual autoregressive (AR) model capable of generating images in arbitrary token orders.
InstructG2I: Synthesizing Images from Multimodal Attributed Graphs
In this paper, we approach an overlooked yet critical task Graph2Image: generating images from multimodal attributed graphs (MMAGs).
RMem: Restricted Memory Banks Improve Video Object Segmentation
With recent video object segmentation (VOS) benchmarks evolving to challenging scenarios, we revisit a simple but overlooked strategy: restricting the size of memory banks.
Frozen Transformers in Language Models Are Effective Visual Encoder Layers
This paper reveals that large language models (LLMs), despite being trained solely on textual data, are surprisingly strong encoders for purely visual tasks in the absence of language.
Ranked #4 on
Question Answering
on SQA3D
Streaming Motion Forecasting for Autonomous Driving
Our benchmark inherently captures the disappearance and re-appearance of agents, presenting the emergent challenge of forecasting for occluded agents, which is a safety-critical problem yet overlooked by snapshot-based benchmarks.
MV-Map: Offboard HD-Map Generation with Multi-view Consistency
To further enhance multi-view consistency, we augment the uncertainty network with the global 3D structure optimized by a voxelized neural radiance field (Voxel-NeRF).
Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking
It emphasizes spatio-temporal continuity and integrates both past and future reasoning for tracked objects.
Embracing Single Stride 3D Object Detector with Sparse Transformer
In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases.
Ranked #3 on
3D Object Detection
on waymo cyclist
Immortal Tracker: Tracklet Never Dies
We employ a simple Kalman filter for trajectory prediction and preserve the tracklet by prediction when the target is not visible.
SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking
3D multi-object tracking (MOT) has witnessed numerous novel benchmarks and approaches in recent years, especially those under the "tracking-by-detection" paradigm.
Ranked #34 on
3D Multi-Object Tracking
on nuScenes
Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences
The code and protocols for our benchmark and algorithm are available at https://github. com/TuSimple/LiDAR_SOT/.
Unlocking the Full Potential of Small Data with Diverse Supervision
Indeed, even the majority of few-shot learning methods rely on a large set of "base classes" for pretraining.
