28 citations · 58 across the 17 of their papers we have counts for
17 papers · 1 filter
One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
Zheyu Zhang, Ziqi Pang, Shixing Chen +3
Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens…
PPTArena: A Benchmark for PowerPoint Editing
Michael Ofengenden, Yunze Man, Ziqi Pang +2
We introduce PPTArena, a benchmark for PowerPoint editing that evaluates how agents modify real slides from natural-language instructions. Unlike benchmarks that rely on image-PDF…
MR. Video: "MapReduce" is the Principle for Long Video Understanding
Ziqi Pang, Yu-Xiong Wang
We propose MR. Video, an agentic long video understanding framework that demonstrates the simple yet effective MapReduce principle for processing long videos: (1) Map: independentl…
Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception
Ziqi Pang, Xin Xu, Yu-Xiong Wang
With the success of image generation, generative diffusion models are increasingly adopted for discriminative tasks, as pixel generation provides a unified perception interface. Ho…
GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation
Lang Lin, Xueyang Yu, Ziqi Pang +1
This paper proposes a novel framework utilizing multi-modal large language models (MLLMs) for referring video object segmentation (RefVOS). Previous MLLM-based methods commonly str…
AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark
Aruna Gauba, Irene Pi, Yunze Man +3
We present AgMMU, a challenging real-world benchmark for evaluating and advancing vision-language models (VLMs) in the knowledge-intensive domain of agriculture. Unlike prior datas…
RandAR: Decoder-only Autoregressive Visual Generation in Random Orders
Ziqi Pang, Tianyuan Zhang, Fujun Luan +5
We introduce RandAR, a decoder-only visual autoregressive (AR) model capable of generating images in arbitrary token orders. Unlike previous decoder-only AR models that rely on a p…
RMem: Restricted Memory Banks Improve Video Object Segmentation
Junbao Zhou, Ziqi Pang, Yu-Xiong Wang
With recent video object segmentation (VOS) benchmarks evolving to challenging scenarios, we revisit a simple but overlooked strategy: restricting the size of memory banks. This di…
Streaming Motion Forecasting for Autonomous Driving
Ziqi Pang, Deva Ramanan, Mengtian Li +1
Trajectory forecasting is a widely-studied problem for autonomous navigation. However, existing benchmarks evaluate forecasting based on independent snapshots of trajectories, whic…
Frozen Transformers in Language Models Are Effective Visual Encoder Layers
Ziqi Pang, Ziyang Xie, Yunze Man +1
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 langu…
MV-Map: Offboard HD-Map Generation with Multi-view Consistency
Ziyang Xie, Ziqi Pang, Yu-Xiong Wang
While bird's-eye-view (BEV) perception models can be useful for building high-definition maps (HD-Maps) with less human labor, their results are often unreliable and demonstrate no…
Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking
Ziqi Pang, Jie Li, Pavel Tokmakov +3
This work proposes an end-to-end multi-camera 3D multi-object tracking (MOT) framework. It emphasizes spatio-temporal continuity and integrates both past and future reasoning for t…
Embracing Single Stride 3D Object Detector with Sparse Transformer
Lue Fan, Ziqi Pang, Tianyuan Zhang +5
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. Overlooking thi…
Immortal Tracker: Tracklet Never Dies
Qitai Wang, Yuntao Chen, Ziqi Pang +2
Previous online 3D Multi-Object Tracking(3DMOT) methods terminate a tracklet when it is not associated with new detections for a few frames. But if an object just goes dark, like b…
SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking
Ziqi Pang, Zhichao Li, Naiyan Wang
3D multi-object tracking (MOT) has witnessed numerous novel benchmarks and approaches in recent years, especially those under the "tracking-by-detection" paradigm. Despite their pr…
Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences
Ziqi Pang, Zhichao Li, Naiyan Wang
Estimating the states of surrounding traffic participants stays at the core of autonomous driving. In this paper, we study a novel setting of this problem: model-free single-object…
Unlocking the Full Potential of Small Data with Diverse Supervision
Ziqi Pang, Zhiyuan Hu, Pavel Tokmakov +2
Virtually all of deep learning literature relies on the assumption of large amounts of available training data. Indeed, even the majority of few-shot learning methods rely on a lar…