REVIEW 6 cited by
MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This research aims to comprehensively explore building a multimodal foundation model for egocentric video understanding. To achieve this goal, we work on three fronts. First, as there is a lack of QA data for egocentric video understanding, we automatically generate 7M high-quality QA samples for egocentric videos ranging from 30 seconds to one hour long in Ego4D based on human-annotated data. This is one of the largest egocentric QA datasets. Second, we contribute a challenging egocentric QA benchmark with 629 videos and 7,026 questions to evaluate the models' ability in recognizing and memorizing visual details across videos of varying lengths. We introduce a new de-biasing evaluation method to help mitigate the unavoidable language bias present in the models being evaluated. Third, we propose a specialized multimodal architecture featuring a novel "Memory Pointer Prompting" mechanism. This design includes a \textit{global glimpse} step to gain an overarching understanding of the entire video and identify key visual information, followed by a fallback step that utilizes the key visual information to generate responses. This enables the model to more effectively comprehend extended video content. With the data, benchmark, and model, we build MM-Ego, an egocentric multimodal LLM that shows powerful performance on egocentric video understanding.
Forward citations
Cited by 6 Pith papers
-
Pro$^2$Assist: Continuous Step-aware Proactive Assistance with Multi-modal Egocentric Perception for Long-horizon Procedural Tasks
Pro²Assist uses multimodal egocentric perception from AR glasses to track fine-grained progress in long-horizon procedural tasks and deliver timely proactive assistance, outperforming baselines by over 21% in action u...
-
EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering
EgoTextVQA, a new 7K-question benchmark for egocentric scene-text aware video QA, shows that all ten tested multimodal LLMs, including Gemini 1.5 Pro, answer fewer than 35% correctly.
-
Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents
Lucid shows that imperceptible image perturbations can make multimodal agents misremember past events with 61.6% poisoning and 58.4% injection success.
-
EgoIntent: A Pre-Outcome Micro-Step Benchmark for Understanding What, Why, and Next
A step-level egocentric-video benchmark for What/Why/Next intent shows current multimodal models score only about 33/100, though some supporting experiments are missing from the paper.
-
Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation
Ego Scene Augmentation boosts egocentric VQA accuracy by 8.14% (indoor) and 8.72% (outdoor) by injecting a Depth-Anything-derived object/depth/text scene graph into the MLLM prompt.
-
The Repeated-Stimulus Confound in Electroencephalography
The repeated-stimulus confound, where models are trained and tested on repeated presentations of identical stimuli, inflates reported EEG decoding accuracies by an estimated 4.46 to 7.42 percent.
Discussion (0). Continue with ORCID to comment.