Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Tat‐Seng ChuaSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works42 from public data
- Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning782
HIPT with hierarchical pretraining outperforms current state-of-the-art methods for cancer subtyping and survival prediction, and self-supervised ViTs are able to model important inductive biases about the hierarchical structure of phenotypes in the tumor microenvironment.
- Can I Trust Your Answer? Visually Grounded Video Question Answering183
NExT-GQA is constructed - an extension of NExT-QA with 10.5K temporal grounding (or location) labels tied to the original QA pairs tied to the original VLMs and aims to push towards trustworthy VLMs in VQA systems.
- Video as Conditional Graph Hierarchy for Multi-Granular Question Answering154
This work proposes to model video as a conditional graph hierarchy which weaves together visual facts of different granularity in a level-wise manner, with the guidance of corresponding textual cues to align with the multi-granular essence of linguistic concepts in language queries.
- Invariant Grounding for Video Question Answering128
A new learning framework is proposed, Invariant Grounding for VideoQA (IGV), to ground the question-critical scene, whose causal relations with answers are invariant across different interventions on the complement, which significantly improves the reasoning ability.
- 82
- Contrastive Video Question Answering via Video Graph Transformer78
With superior video encoding and QA solution, it is shown that CoVGT can achieve much better performances than previous arts on video reasoning tasks and can also benefit from cross-modal pretraining, yet with orders of magnitude smaller data.
- 77
- Interventional Video Relation Detection73
This paper proposes an Interventional Video Relation Detection approach that aims to improve not only the accuracy but also the robustness of the model prediction, and applies a causality-inspired intervention on the model input subject, object, which forces the model to fairly incorporate each possible predicate prototype into consideration.
- EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering61
This work introduces EgoTextVQA, a novel and rigorously constructed benchmark for egocentric QA assistance involving scene text, and comprehensively evaluates 10 prominent multimodal large language models.
- Video Visual Relation Detection via Iterative Inference55
This work derives their model from the viewpoint of joint relation classification which is light-weight yet effective, and proposes a training approach to better learn the dependency knowledge from the likely correct triplet combinations.
- VideoQA in the Era of LLMs: An Empirical Study39
This work conducts a timely and comprehensive study of Video-LLMs’ behavior in VideoQA, aiming to elucidate their success and failure modes, and provide insights towards more human-like video understanding and question answering.
- Equivariant and Invariant Grounding for Video Question Answering38
A self-interpretable framework, Equivariant and Invariant Grounding for Interpretable VideoQA (EIGV), which is able to distinguish the causal scene from the environment information, and explicitly present the visual-linguistic alignment.
- Discovering Spatio-Temporal Rationales for Video Question Answering30
TranSTR is proposed, a Transformerstyle neural network architecture that takes STR as the core and additionally underscores a novel answer interaction mechanism to coordinate STR for answer decoding that achieves new state-of-the-art (SoTA) results.
- Redundancy-aware Transformer for Video Question Answering27
A novel transformer-based architecture is proposed, that aims to model VideoQA in a redundancy-aware manner, and introduces a video encoder structure that emphasizes the object-level change in neighboring frames, while adopting an out-of-neighboring message-passing scheme that imposes attention only on distant frames.
- 26
- VidVRD 202120
This paper makes a comprehensive and detailed introduction of this task, concludes the proposed algorithms in the last few years, and proposes future direction for research in this task.
- Overexpression screen of chromosome 21 genes reveals modulators of Sonic hedgehog signaling relevant to Down syndrome17
It is suggested that cerebellar hypoplasia and other phenotypes related to aberrant SHH signaling arise from the net effect of trisomy for multiple chromosome 21 genes rather than the overexpression of a single trisomic gene.
- Understanding Long Videos via LLM-Powered Entity Relation Graphs15
GraphVideoAgent is a cutting-edge system that leverages the power of graph-based object tracking in conjunction with large language model capabilities that enables more nuanced understanding of how objects interact and transform over time, facilitating improved frame selection through comprehensive contextual awareness.
- GraphVideoAgent: Enhancing Long-form Video Understanding with Entity Relation Graphs12
GraphVideoAgent is proposed, a novel agent-based LVU framework that integrates a dynamic entity relation graph with a large language model (LLM)-based multi-round reasoning that enables accurate keyframe selection, effective reasoning over sparse visual evidence, and interpretable prediction.
- X-Ray2EM: Uncertainty-Aware Cross-Modality Image Reconstruction from X-Ray to Electron Microscopy in Connectomics7
An uncertainty-aware 3D reconstruction model is proposed that translates X-ray images to EM-like images with enhanced membrane segmentation quality, showing its potential for developing simpler, faster, and more accurate X-rays based connectomics pipelines.
- 5
- Visual feature synthesis with semantic reconstructor for traditional and generalized zero‐shot object classification5
A novel named semantic consistent Wasserstein generative adversarial network (scWGAN) is proposed, which uses a semantic reconstructor to reconstruct semantic embeddings from generated visual features by incorporating a novel Semantic Consistent Loss noted L rec .
- The XPRESS Challenge: Xray Projectomic Reconstruction -- Extracting Segmentation with Skeletons4
This task provides volumetric XNH images of cortical white matter axons from the mouse brain along with ground truth annotations for axon trajectories along with two types of ground-truth annotations: a small volume of voxel-wise annotations and a larger volume with skeleton-based annotations.
- 4
- AnchorDS: Anchoring Dynamic Sources for Semantically Consistent Text-to-3D Generation2
This work reformulates text‑to-3D optimization as mapping a *dynamically evolving source* distribution to a fixed target distribution, and introduces AnchorDS, an improved score distillation mechanism that provides state‑anchored guidance with image conditions and stabilizes generation.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.